Wyniki wyszukiwania - BazTech

1

Gas turbine vibration monitoring based on real data and neuro-fuzzy system

Nail Bachir, Djaidir Benrabeh, Tibermacine Imad Eddine, Napoli Christian, Haidour Nabil, Abdelaziz Rabehi

Diagnostyka

|

2024

|

Vol. 25, No. 1

art. no. 2024108

EN

The gas turbine is considered to be a very complex piece of machinery because of both its static structure and the dynamic behavior that results from the occurrence of vibration phenomena. It is required to adopt monitoring and diagnostic procedures for the identification and localization of vibration flaws in order to ensure the appropriate operation of large rotating equipment such as gas turbines. This is necessary in order to avoid catastrophic failures and deterioration and to ensure that proper operation occurs. Utilizing an approach that is based on spectrum analysis, the purpose of this study is to provide a model for the monitoring and diagnosis of vibrations in a GE MS3002 gas turbine and its driven centrifugal compressor. This will be done by utilizing the technique. Following that, the collection of vibration measurements for a model of the centrifugal compressor served as a suggestion for an additional method. This method is based on the neuro-fuzzy approach type ANFIS, and it aims to create an equivalent system that is able to make decisions without consulting a human being for the purpose of detecting vibratory defects. In spite of the fact that the compressor that was investigated has flaws, this procedure produced satisfactory results.

2

ANFIS based inverse controller design for liquid level control of a spherical tank

Akca Talha Burak, Ulu Cenk, Obut Salih

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 2

32--36

EN

In this study, an adaptive neuro fuzzy inference system (ANFIS) based inverse controller design is presented for liquid level control application of a spherical tank. First, an excitation signal is applied to the system and the corresponding output signal is obtained. ANFIS-based fuzzy model of the nonlinear spherical tank system is constructed by using this input-output data set. While constructing the fuzzy model, a fuzzy model structure with two inputs and one output is preferred considering design simplicity. The input-output data used for constructing the fuzzy model of the system are exchanged, and by using this new data set, an ANFIS based inverse controller is designed. To improve the control performance against disturbances and model mismatches, the inverse controller is used in an internal model control structure. The performance of the proposed controller is compared to that of classical PI and fuzzy PI controllers under set point variation and disturbance conditions. The results of comparisons reveal that the proposed inverse controller outperforms both the classical and fuzzy PI controllers.

PL

W niniejszym opracowaniu przedstawiono projekt regulatora odwrotnego opartego na adaptacyjnym neurorozmytym systemie wnioskowania (ANFIS) do zastosowania w kontroli poziomu cieczy w zbiorniku kulistym. Najpierw do systemu doprowadzany jest sygnał wzbudzenia i uzyskiwany jest odpowiedni sygnał wyjściowy. Oparty na ANFIS model rozmyty nieliniowego systemu zbiorników sferycznych jest tworzony przy użyciu tego zestawu danych wejściowych i wyjściowych. Podczas konstruowania modelu rozmytego preferowana jest struktura modelu rozmytego z dwoma danymi wejściowymi i jednym wynikiem, biorąc pod uwagę prostotę projektowania. Dane wejściowe-wyjściowe wykorzystywane do budowy modelu rozmytego systemu są wymieniane, a przy użyciu tego nowego zestawu danych projektowany jest sterownik odwrotny oparty na ANFIS. W celu poprawy wydajności sterowania w przypadku zakłóceń i niezgodności modelu, w wewnętrznej strukturze sterowania modelu zastosowano regulator odwrotny. Wydajność proponowanego regulatora jest porównywana z klasycznymi regulatorami PI i rozmytymi regulatorami PI w warunkach zmienności wartości zadanej i zakłóceń. Wyniki porównań pokazują, że proponowany regulator odwrotny przewyższa zarówno klasyczne, jak i rozmyte regulatory PI.

3

Forecasting the Flow Coefficient of the River Basin Using Adaptive Fuzzy Inference System and Fuzzy SMRGT Method

Gunal Ayse Yeter, Mehdi Ruya

Journal of Ecological Engineering

|

2023

|

Vol. 24, nr 7

96--107

EN

In hydrology and water resources engineering, predicting the flow coefficient is a crucial task that helps estimate the precipitation resulting in a surface flow. Accurate flow coefficient prediction is essential for efficient water management, flood control strategy development, and water resource planning. This investigation calculated the flow coefficient using models based on Simple Membership functions and fuzzy Rules Generation Technique (SMRGT) and an Adaptive Neuro-Fuzzy Inference System (ANFIS) model. The fuzzy logic methods are used to model the intricate connections between the inputs and the output. Statistical parameters such as the coefficient of determination (R2), the root mean square error (RMSE), the mean absolute error (MAE), and the mean absolute percentage error (MAPE) were used to evaluate the performance of models. The statistical tests outcome for the SMRGT model was (RMSE:0.056, MAE:1.92, MAPE:6.88, R2:0.996), and for the ANFIS was (RMSE:0.96, MAE:2.703, MAPE:19.97, R2:0.8038). According to the findings, the SMRGT, a physics-based model, exhibited superior accuracy and reliability in predicting the flow coefficient compared to ANFIS. This is attributed to the SMRGT’s ability to integrate expert knowledge and domain-specific information, rendering it a viable solution for diverse issues.

4

An explainable AI approach to agrotechnical monitoring and crop diseases prediction in Dnipro region of Ukraine

Laktionov Ivan, Diachenko Grigorii, Rutkowska Danuta, Kisiel-Dorohinicki Marek

Journal of Artificial Intelligence and Soft Computing Research

|

2023

|

Vol. 13, No. 4

247--272

EN

The proliferation of computer-oriented and information digitalisation technologies has become a hallmark across various sectors in today’s rapidly evolving environment. Among these, agriculture emerges as a pivotal sector in need of seamless incorporation of highperformance information technologies to address the pressing needs of national economies worldwide. The aim of the present article is to substantiate scientific and applied approaches to improving the efficiency of computer-oriented agrotechnical monitoring systems by developing an intelligent software component for predicting the probability of occurrence of corn diseases during the full cycle of its cultivation. The object of research is non-stationary processes of intelligent transformation and predictive analytics of soil and climatic data, which are factors of the occurrence and development of diseases in corn. The subject of the research is methods and explainable AI models of intelligent predictive analysis of measurement data on the soil and climatic condition of agricultural enterprises specialised in growing corn. The main scientific and practical effect of the research results is the development of IoT technologies for agrotechnical monitoring through the development of a computer-oriented model based on the ANFIS technique and the synthesis of structural and algorithmic provision for identifying and predicting the probability of occurrence of corn diseases during the full cycle of its cultivation.

5

Comparison of machine learning models for predicting groundwater level, case study: Najafabad region

Zarafshan Pejman, Etezadi Hamed, Javadi Saman, Roozbahani Abbas, Hashemy S. Mehdi, Zarafshan Payam

Acta Geophysica

|

2023

|

Vol. 71, no. 4

1817--1830

EN

Water resources, consisting of surface water and groundwater, are considered to be among the crucial natural resources in most arid and semiarid regions. Groundwater resources as the sustainable yields can be predicted, whereas this is one of the important stages in water resource management. To this end, several models such as mathematical, statistical, empirical, and conceptual can be employed. In this paper, machine learning and deep learning methods as conceptual ones are applied for the simulations. The selected models are support vector regression (SVR), adaptive neuro-fuzzy inference system (ANFIS), and multilayer perceptron (MLP). Next, these models are optimized with the adaptive moment estimation (ADAM) optimization algorithm which results in hybrid models. The hyper-parameters of the stated models are optimized with the ADAM method. The root mean squared error (RMSE), mean absolute error (MAE), mean squared error (MSE), and coefficient of determination (R2) are used to evaluate the accuracy of the simulated groundwater level. To this end, the aquifer hydrograph is used to compare the results with observations data. So, the RMSE and R2 show that the accuracy of the machine learning and deep learning models is better than the numerical model for the given data. Moreover, the MSE is approximately the same in all three cases (ranging from 0.7113 to 0.6504). Also, the total value of R2 and RMSE for the best hybrid model is 0.9617 and 0.7313, respectively, which are obtained from the model output. The results show that all three techniques are useful tools for modeling hydrological processes in agriculture and their computational capabilities and memory are similar.

6

The influence of rainfall time series fractality on forecasting models’ efficiency

Rahmani Farhang, Fattahi Mohammad Hadi

Acta Geophysica

|

2022

|

Vol. 70, no 3

1349--1361

EN

Forecasting rainfall time series is of great significance for hydrologists and geoscientists. Thus, this study represents a contribution to understanding the impact of the fractal time series variety on forecasting model performance. Multiple fractal series were generated via p-model and used for modeling. Subsequently, the forecasting was delivered based on existing observed monthly rainfall data (three stations in the UK, from 1865 to 2002) through five forecasting models. Finally, the association between series fractality and models’ performance was examined. The results indicated that the forecasting based on the mono-fractal series resulted in the most reliable results (R2=1 and RMSE less than 0.02). In the case of multifractal series, modeling based on series with the right side of the asymmetric curve of the multifractal spectrum presented series with the lowest RMSE (0.96) and highest R2 (0.99) (desirable performance). In contrast, the forecasting based on series with the left side of the asymmetric curve of the multifractal spectrum suggested the most unreliable outcomes (R2 range [−0.0007 ~ 0.988] and RMSE range [0.8526 ~ 39.3]). The forecasting based on the symmetric curve of the multifractal spectrum series delivered regular performance. Accordingly, high and low errors are expected from forecasting based on the time series with a left-skewed multifractal spectrum and right-skewed multifractal spectrum (and mono-fractal time series), respectively. Hybrid models were the best options for forecasting mono-fractal and multifractal time series with right side asymmetric and symmetric multifractal spectrum curves. The ARIMA model was suitable to predict multifractal time series with left side asymmetric multifractal spectrum curves.

7

Neuro fuzzy based SSSC for active and reactive power control in AC lines with reduced oscillation

Alkhayyat M. T., Suliman Mohammed Y.

Przegląd Elektrotechniczny

|

2021

|

R. 97, nr 3

75--79

EN

The FACTS (Flexible AC Transmission System) devices have been considered as excellent controllers in a power system for better reliability and transmission capacity on a long-term and cost-effective basis. The static synchronous series compensator (SSSC) is one of robust FACTS devices that can control the flow of power in AC lines. In this paper, modelling and simulation of active and reactive power flow control in transmission lines and voltage control using SSSC with adaptive neuro-fuzzy logic is proposed. The mathematical model of SSSC in power flow is also proposed. The results show the ability of SSSC to control the flow of power in the AC lines of power system within line voltage limitations.

PL

Przedstawiono modelowanie i symulację sterowania przepływem mocy czynnej I biernej przy wykorzystaniu SSSC (synchroniczne kompensatory szeregowe) oraz zastosowaniu adaptacyjnej logiki neuro-fuzzy. Przedstawiono model matematyczny systemu SSSC.

8

Trend and prediction of COVID-19 outbreak in Iran: SEIR and ANFIS model

Shafiekhani Sajad, Khalilabad Touraj Harati, Rafiei Sima, Sadeghi Vahid, Jafari Amir Homayoun, Gheibi Nematollah

Polish Journal of Medical Physics and Engineering

|

2021

|

Vol. 27, Iss. 3

241--249

EN

Background: Mathematical and predictive modeling approaches can be used in COVID-19 crisis to forecast the trend of new cases for healthcare management purposes. Given the COVID-19 disease pandemic, the prediction of the epidemic trend of this disease is so important. Methods: We constructed an SEIR (Susceptible-Exposed-Infected-Recovered) model on the COVID-19 outbreak in Iran. We estimated model parameters by the data on notified cases in Iran in the time window 1/22/2020 – 20/7/2021. Global sensitivity analysis is performed to determine the correlation between epidemiological variables and SEIR model parameters and to assess SEIR model robustness against perturbation to parameters. We Combined Adaptive Neuro- Fuzzy Inference System (ANFIS) as a rigorous time series prediction approach with the SEIR model to predict the trend of COVID-19 new cases under two different scenarios including social distance and non-social distance. Results: The SEIR and ANFIS model predicted new cases of COVID-19 for the period February 7, 2021, till August 7, 2021. Model predictions in the non-social distancing scenario indicate that the corona epidemic in Iran may recur as an immortal oscillation and Iran may undergo a recurrence of the third peak. Conclusion: Combining parametrized SEIR model and ANFIS is effective in predicting the trend of COVID-19 new cases in Iran.

9

An adaptive neuro-fuzzy based methodology for harmonic analysis of a power transformer

Urooj Shabana, Amir Mohammad, Khan Aiman, Tariq Mohd

Journal of Power Technologies

|

2021

|

Vol. 101, nr 1

1--10

EN

The interfering nature of harmonics always causes various power quality issues that impacts on both efficiency, and expected transformer life. Optimal analysis of the three-phase core power transformers using harmonic spectrum can limit these power quality issues. This paper designs the Adaptive Neuro-Fuzzy Inference System (ANFIS) based model for the estimation of losses. Further optimal parameters selection of three-phase power transformer using iron and ferrite core materials. This paper demonstrates factors that deteriorate the power quality, responsible for harmonics distortions and inefficiency in power transformers. The proposed ANFIS based analysis provides an optimal solution to harmonic reduction and improves overall efficiency. Also, providing a comparative study of various core parameters that will be suitable for a three-phase core transformer. The proposed parameters are demonstrated for improving the overall transformer efficiency using iron and ferrite core material. ANSYS Maxwell simulation estimates the Total Harmonic Distortion (THD) and enhances THD in contributing to the optimal core material. The design of a three-phase power transformer and the performance evaluation of the proposed methodology performed in MATLAB simulation environment.

10

Forecasting the electricity generation of photovoltaic plants

Kuievda Iuliia, Baliuta Serhii, Zinkevich Petro, Stoliarov Oleksandr

Journal of New Technologies in Environmental Science

|

2021

|

Vol. 5, nr 1

40--45

EN

Due to the need in accordance with Ukrainian legislation to submit a day-ahead hourly forecast of electricity generation of solar power plants, the problem of forecasting model quality becomes very important. In the study it is proposed a method of choosing the optimal structure and sensitivity assessment of ANFIS-based forecasting model. In the model the input is solar irradiance, the output is solar panel generation power. The method is based on computational procedures using MATLAB software. For the data set, used in the study, the results, optimal for normalized mean absolute error (NMAE), were achieved on 5 triangular input member functions (trimf), while the error varied within 0.23% depending on number and shape of input member functions. According to the calculations of input error sensitivity of the forecasting model with 5 input trimf membership functions, the increasing of input error up to 8.19% NMAE leads to the raising of the output error in the testing sample up to 5.78%, NMAE. The rather low sensitivity of the model to the input data error allows us to conclude that forecasted meteorological data with a pre-known fixed forecast error can be used as input data.

11

Predictive models for estimation of labyrinth weir aeration efficiency

Aradhana Aradhana, Singh B., Sihag P.

Journal of Achievements in Materials and Manufacturing Engineering

|

2021

|

Vol. 105, nr 1

18--32

EN

Purpose: The purpose of the study is to estimate the aeration efficiency (E20) of Labyrinth weir using artificial intelligent (AI)-based models. Design/methodology/approach: The aeration efficiency (E20) was collected by using the nine models of Labyrinth weir with different shapes and dimensions. A total of 180 observations were used out of which 126 used to train the AI-based models and the remaining used to test the model. This observation consists of input variables such as Fraud number (Fr), Reynolds number (Re), numbers of keys (N), the ratio of head to the width of the channel (H/W), the ratio of crest length to width of the channel (L/W), the ratio of drop height to width of the channel (D/W) and shape factor (SF) and E20 as the output variables. The AI-based models used were Fuzzy Logic, multi-linear regression (MLR), adaptive neuro fuzzy interface system (ANFIS), and artificial neural network (ANN). Findings: The main findings of this investigation are that ANN is the best AI-based model that can estimate the E20 accurately than MLR, ANFIS, and Fuzzy Logic. Sensitivity analysis depicts that drop height at labyrinth weir is the essential factors for the estimation of E20; further, parametric studies have also been performed. Research limitations/implications: The proposed AI-based models can be used in the estimation of E20 with different shapes of labyrinth weir but still it needs improvement for the different dimensions. Practical implications: The best AI-based model can be used to calculate the E20 with the different values of input variables. Originality/value: There are no such AI-based models such as ANN, ANFIS, and Fuzzy Logic, available in the literature which can estimate the values of E20 accurately.

12

Modelling electricity production structure in Poland

Sowiński Janusz

Rynek Energii

|

2020

|

Nr 3

79--85

EN

The basis of the conducted analysis were the data on electricity production balance, including the structure of eleltricity production. The data used for calculations include monthly electricity production figures from power plants (thermal and hydro electric power plants, wind farms), independent power producers and industrial power stations. In this paper, two predictive models are applied – a prediction method using Adaptive Neuro-Fuzzy Inference System (ANFIS), and a method using stochastic differential equations (SDE), which make it possible to make medium-term projections of electricity production and its structure, thus providing the basis for energy mix analysis. The results of estimations and verification of the developed models are presented, as well as examples of prediction results. The results were compared to the projection provided in the draft of Polityka Energetyczna Polski do 2040 roku PEP2040 (Poland’s Energy Policy until 2040). An attempt was also made to answer the question whether the models based only on historical time series may serve as a valid basis for the analysis of electricity production structure, and whether such models are capable of adequately describing the processes in power engineering under uncertainty and risk.

PL

Dane dotyczące bilansu w zakresie wytwarzania energii elektrycznej z uwzględnieniem jej struktury są podstawą wykonanych analiz. Dane wykorzystywane do obliczeń zawierają miesięczne produkcje energii elektrycznej z elektrowni zawodowych (termiczne, wodne i wiatrowe), niezależnych producentów energii elektrycznej oraz przemysłowych elektrociepłowni. W artykule wykorzystano dwa modele predykcji, metodę predykcji z wykorzystaniem rozmytego systemu wnioskowania ANFIS - Adaptive Neuro-Fuzzy Inference System i metodę wykorzystującą stochastyczne równania różniczkowe SDE – Stochastic Differential Equations, umożliwiające wykonanie średnioterminowej prognozy produkcji energii elektrycznej wraz z jej strukturą, dając podstawę do analizy mixu energetycznego. Zaprezentowano wyniki estymacji i weryfikacji budowanych modeli oraz przykładowe wyniki predykcji. Rezultaty porównano z prognozą prezentowaną w projekcie Polityki Energetycznej Polski do 2040 roku PEP2040. W tym kontekście podjęto dyskusję w celu odpowiedzi na pytanie, czy modele bazujące tylko na historycznych szeregach chronologicznych mogą być podstawą analiz struktury wytwarzania energii elektrycznej i czy są adekwatne do opisu procesów w elektroenergetyce w warunkach niepewności i ryzyka.

13

Development of an adaptive neuro-fuzzy inference system (ANFIS) model to predict sea surface temperature (SST)

Kale Semih

Oceanological and Hydrobiological Studies

|

2020

|

Vol. 49, No. 4

354--373

EN

An accurate estimation of the sea surface temperature (SST) is of great importance. Therefore, the objective of this work was to develop an adaptive neuro-fuzzy inference system (ANFIS) model to predict SST in the Çanakkale Strait. The observed monthly air temperature, evaporation and precipitation data from the Çanakkale meteorological observation station were used as input data. The Takagi–Sugeno fuzzy inference system was applied. The grid partition method (ANFIS-GP) and the subtractive clustering partitioning method (ANFIS-SC) were used with Gaussian membership functions to generate the fuzzy inference system. Six performance evaluation criteria were used to evaluate the developed SST prediction models, including mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), Nash-Sutcliffe efficiency (NSE) and correlation of determination (R2). The dataset was randomly divided into training and testing datasets for the machine learning process. Training data accounted for 75% of the dataset, while 25% of the dataset was allocated for testing in ANFIS. The hybrid algorithm was selected as a training algorithm for the ANFIS. Simulation results revealed that the ANFIS-SC4 model provided a higher correlation coefficient of 0.96 between the observed and predicted SST values. The results of this study suggest that the developed ANFIS model can be applied for predicting sea surface temperature around the world.

14

Methodology for monitoring and diagnosing faults of hybrid dynamic systems: a case study on a desalination plant

Achbi Mohammed Said, Kechida Sihem

Diagnostyka

|

2020

|

Vol. 21, No. 1

27--33

EN

The imperative of quality and productivity has increased the complexity of technological processes, posing the problem of reliability. Today, fault diagnosis remains a very important task because of its essential role in improving reliability, but also in minimizing the harmful consequences that can be catastrophic for the safety of equipment and people. Indeed, an effective diagnosis not only improves reliability, but also reduces maintenance costs. Systems in which dynamic behaviour evolves as a function of the interaction between continuous dynamics and discrete dynamics, present in the system, are called hybrid systems. The goal is to develop monitoring and diagnostic procedures to the highest level of control to ensure safety, reliability and availability objectives. This article presents an approach to the diagnosis of hybrid systems using hybrid automata and neural-fuzzy system. The use of the neural-fuzzy system allows modeling the continuous behaviour of the system. On the other hand, the hybrid automata gives a perfect estimate of the discrete events and make it possible to execute a fault detection algorithm mainly consists of classifying the appeared defects. On the implementation plan, the results were applied in a water desalination plant.

15

ANFIS-based PID continuous sliding mode controller for robot manipulators in joint space

Elawady Wael M., Asar Mohammed F., Sarhan Amany M.

Control and Cybernetics

|

2019

|

Vol. 48, No. 4

525--555

EN

This paper presents a feasible design for a con- trol algorithm to synthesize an adaptive neuro-fuzzy inference system-based PID continuous sliding mode control system (ANFIS- PIDCSMC) for adaptive trajectory tracking control of the rigid robot manipulators (RRMs) in the joint space. First, a PID sliding mode control algorithm with sliding surface dynamics-based continuous proportional-integral (PI) control action (PIDSMC-SSDCPI) is presented. The global stability conditions are formulated in terms of Lyapunov full quadratic form such that the robot system output can track the desired reference output. Second, to increase the control system robustness, the PI control action in the PIDSMC- SSDCPI controller is supplanted by an ANFIS control signal to provide a control approach that can be termed adaptive neuro-fuzzy inference system-based PID continuous sliding mode control system (ANFIS-PIDCSMC). For the proposed control algorithm, numerical simulations using the dynamic model of RRM with uncertainties and external disturbances show high quality and effectiveness of the adopted control approach in high-speed trajectory tracking control problems. The simulation results that are compared with the results, obtained for the traditional controllers (standalone PID and traditional sliding mode controller (TSMC)), illustrate the fact that the tracking control behavior of the robot system achieves acceptable tracking performance.

16

Artificial intelligence approaches for spatial modeling of streambed hydraulic conductivity

Deka Paresh Chandra, Naganna Sujay Raghavendra

Acta Geophysica

|

2019

|

Vol. 67, no. 3

891--903

EN

Saturated hydraulic conductivity (Ks) describes the water movement through saturated porous media. The hydraulic conductivity of streambed varies spatially owing to the variations in sediment distribution profiles all along the course of the stream. The artificial intelligence (AI) based spatial modeling schemes were instituted and tested to predict the spatial patterns of streambed hydraulic conductivity. The geographical coordinates (i.e., latitude and longitude) of the sampled locations from where the in situ hydraulic conductivity measurements were determined were used as model inputs to predict streambed Ks over spatial scale using artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and support vector machine (SVM) paradigms. The statistical measures computed by using the actual versus predicted streambed Ks values of individual models were comparatively evaluated. The AI-based spatial models provided superior spatial Ks prediction efficiencies with respect to both the strategies/schemes considered. The model efficiencies of spatial modeling scheme 1 (i.e., Strategy 1) were better compared to Strategy 2 due to the incorporation of more number of sampling points for model training. For instance, the SVM model with NSE = 0.941 (Strategy 1) and NSE = 0.895 (Strategy 2) were the best among all the models for 2016 data. Based on the scatter plots and Taylor diagrams plotted, the SVM model predictions were found to be much efficient even though, the ANFIS predictions were less biased. Although ANN and ANFIS models provided a satisfactory level of predictions, the SVM model provided virtuous streambed Ks patterns owing to its inherent capability to adapt to input data that are non-monotone and nonlinearly separable. The tuning of SVM parameters via 3D grid search was responsible for higher efficiencies of SVM models.

17

Application of fuzzy analytic hierarchy process to building research teams

Dąbrowski K., Skrzypek K.

Management Systems in Production Engineering

|

2016

|

nr 1 (21)

7--11

EN

Building teams has a fundamental impact for execution of research and development projects. The teams appointed for the needs of given projects are based on individuals from both inside and outside of the organization. Knowledge is not only a product available on the market but also an intangible resource affecting their internal and external processes. Thus it is vitally important for businesses and scientific research facilities to effectively manage knowledge within project teams. The article presents a proposal to use Fuzzy AHP (Analytic Hierarchy Process ) and ANFIS (Adaptive Neuro Fuzzy Inference System) methods in working groups building for R&D projects on the basis of employees skills.

PL

Budowanie zespołów ma podstawowe znaczenie dla realizacji projektów badawczych i rozwojowych. Zespoły powołane na potrzeby określonych projektów oparte są o osoby z wewnątrz i z zewnątrz organizacji. Wiedzy nie można traktować tylko jako jeden z produktów dostępnych na rynku, ale także jako zasób niematerialny, który wpływa na procesy wewnętrzne i zewnętrzne. Tak więc jest to niezwykle istotny potencjał dla firm i naukowych ośrodków badawczych, który ma wpływ na skuteczne zarządzanie wiedzą w zespołach projektowych. W artykule przedstawiono propozycję wykorzystania metod Fuzzy AHP (Analytic Hierarchy Process) i ANFIS (Adaptive Neuro Fuzzy Inference System) w budowaniu, kompletowaniu zespołów do realizacji projektów B + R na podstawie kwalifikacji pracowników.

18

Resource Monitoring for Wireless Sensor Networks using ANFIS

Nagesha S., Manvi S. S.

Journal of Applied Computer Science Methods

|

2016

|

Vol. 8 No. 1

41--67

EN

Wireless sensor networks (WSNs) are usually a resource constrained networks which have limited energy, bandwidth, processing power, memory etc. These networks are now part of Internet by the name Internet of Things (IoT). To get many services from WSNs, we may need to run many applications in the sensor nodes which consumes resources. Ideally, the resources availability of all sensor nodes should be known to the sink before it requests for any further service(s) from the sensor node(s). Hence, continuous monitoring of the resources of the sensor nodes by the sink is essential. The proposed work is a framework for monitoring certain important resources of sensor network using Adaptive-Neuro Fuzzy Inference System (ANFIS) and Constrained Application Protocol (CoAP). The ANFIS is trained with these resources consumption patterns. The input to ANFIS is the resources consumption levels and the output is the resources consumed levels that needs to be sent to the sink which may be individual or combinations of resources. The trained ANFIS generates the output periodically which determines resources consumption levels that needs to be sent to the sink. Also, ANFIS continuously learns using hybrid learning algorithm (which is basically a combination of back propagation and least squares method) and updates its parameters for better results. The CoAP protocol with its observe option is used to transport the resource monitoring data from the sensor nodes to the cluster head, then from the cluster head to the sink. The sensor nodes runs coap server, the cluster head runs both coap client and server and the sink runs coap client. The performance of the proposed work is compared with LoWPAN network management protocol (LNMP) and EmNets Network Management Protocol (EMP) in terms of bandwidth and energy overheads. It is observed that proposed work performs better when compared to the existing works.

19

Faults detection in gas turbine using hybrid adaptive network based fuzzy inference systems

Hadroug N., Hafaifa A., Kouzou A., Chaibet A.

Diagnostyka

|

2016

|

Vol. 17, No. 4

3--17

EN

The main aim of the present paper is the implementation of a fault detection strategy to ensure the fault detection in a gas turbine which is presenting a complex system. This strategy is based on an adaptive hybrid neuro fuzzy inference technique which combines the advantages of both techniques of neuron networks and fuzzy logic, where, the objective is to maintain the desired performance of the studied gas turbine system in the presence of faults. On the other side, the representation of fuzzy knowledge in the learning neural networks has to be accurate to provide significant improvements for modeling of the studied system dynamic behavior. The results presented in this paper proves clearly that the proposed detection technique allows the perfect detection of the studied gas turbine malfunctions, furthermore it shows that the use of the proposed technique based on the Adaptive Neuro-Fuzzy Interference System (ANFIS) approach which uses the adaptive learning mechanism of neuron networks and fuzzy inference techniques, can be a promising technique to be applied in several industrial application for faults detection.

20

Statistical modeling of copper losses in the silicate slag of the sulfide concentrate smelting process

Savic M. V., Djordjevic P. B., Mihajlovic I. N., Zivkovic Z. D.

Polish Journal of Chemical Technology

|

2015

|

Vol. 17, nr 3

62--69

EN

This article presents the results of the statistical modeling of copper losses in the silicate slag of the sulfide concentrates smelting process. The aim of this study was to define the correlation dependence of the degree of copper losses in the silicate slag on the following parameters of technological processes: SiO2, FeO, Fe3O4, CaO and Al2O3 content in the slag and copper content in the matte. Multiple linear regression analysis (MLRA), artificial neural networks (ANNs) and adaptive network based fuzzy inference system (ANFIS) were used as tools for mathematical analysis of the indicated problem. The best correlation coefficient (R2 = 0.719) of the final model was obtained using the ANFIS modeling approach.