Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 173
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

The paper presents the possibilities of neural network application in recognition of rotor blade faults. Computer calculated data of rotor response due to faults were used for neural network training. The rotor was modeled by elastic axes with distribution of Jumped masses. The rotor defects were simulated by changing aerodynamic, inertial or stiffness properties of one of the blades. Time results were subjected to spectral analysis for the purpose of neural networks training.
Go to article

Authors and Affiliations

Jarosław Stanisławski
Download PDF Download RIS Download Bibtex

Abstract

The paper presents the operation of two neuro-fuzzy systems of an adaptive type, intended for solving problems of the approximation of multi-variable functions in the domain of real numbers. Neuro-fuzzy systems being a combination of the methodology of artificial neural networks and fuzzy sets operate on the basis of a set of fuzzy rules “if-then”, generated by means of the self-organization of data grouping and the estimation of relations between fuzzy experiment results. The article includes a description of neuro-fuzzy systems by Takaga-Sugeno-Kang (TSK) and Wang-Mendel (WM), and in order to complement the problem in question, a hierarchical structural self-organizing method of teaching a fuzzy network. A multi-layer structure of the systems is a structure analogous to the structure of “classic” neural networks. In its final part the article presents selected areas of application of neuro-fuzzy systems in the field of geodesy and surveying engineering. Numerical examples showing how the systems work concerned: the approximation of functions of several variables to be used as algorithms in the Geographic Information Systems (the approximation of a terrain model), the transformation of coordinates, and the prediction of a time series. The accuracy characteristics of the results obtained have been taken into consideration.
Go to article

Authors and Affiliations

Maria Mrówczyńska
Download PDF Download RIS Download Bibtex

Abstract

Land surveyors, photogrammetrists, remote sensing engineers and professionals in the Earth sciences are often faced with the task of transferring coordinates from one geodetic datum into another to serve their desired purpose. The essence is to create compatibility between data related to different geodetic reference frames for geospatial applications. Strictly speaking, conventional techniques of conformal, affine and projective transformation models are mostly used to accomplish such task. With developing countries like Ghana where there is no immediate plans to establish geocentric datum and still rely on the astro-geodetic datums as it national mapping reference surface, there is the urgent need to explore the suitability of other transformation methods. In this study, an effort has been made to explore the proficiency of the Extreme Learning Machine (ELM) as a novel alternative coordinate transformation method. The proposed ELM approach was applied to data found in the Ghana geodetic reference network. The ELM transformation result has been analysed and compared with benchmark methods of backpropagation neural network (BPNN), radial basis function neural network (RBFNN), two-dimensional (2D) affine and 2D conformal. The overall study results indicate that the ELM can produce comparable transformation results to the widely used BPNN and RBFNN, but better than the 2D affine and 2D conformal. The results produced by ELM has demonstrated it as a promising tool for coordinate transformation in Ghana.

Go to article

Authors and Affiliations

Yao Yevenyo Ziggah
Yakubu Issaka
Prosper Basommi Laari
Zhenyang Hui
Download PDF Download RIS Download Bibtex

Abstract

Artificial neural networks are gaining popularity thank to their fast and accurate response paired with low computing power requirements. They have been proven as a method for compressor performance prediction with satisfactory results. In this paper a new approach of artificial neural networks modelling is evaluated. The auxiliary parameter of ‘relative stability margin Z’ was introduced and used in learning process. This approach connects two methods of compressor modelling such as neuralnetworks and auxiliary parameter utilization. Two models were created, one with utilization of the ‘relative stability margin Z’ as a direct indication of surge margin of any estimated condition, and other with standard compressor parameters. The results were compared by determination of fitting, interpolation and extrapolation capabilities of both approaches. The artificial neural networks used during the process was a two-layer feed-forward neural-network with Levenberg–Marquardt algorithm with Bayesian regularization. The experimental data was interpolated to increase the amount of learning data for the neural network. With the two models created, capabilities of this relatively simple type of neural-network to approximate compressor map was also assessed.
Go to article

Bibliography

[1] Sieber J.: European Technology Programs for Eco-Efficient Ducted Turbofans. ISABE-2015-20029, 2015.
[2] European Commission, Directorate-General for Mobility and Transport, Directorate- General for Research and Innovation. Flightpath 2050: Europe’s vision for aviation: maintaining global leadership and serving society’s needs. Publications Office, 2011.
[3] Orkisz M., Stawarz S.: Modeling of turbine engine axial-flow compressor and turbine characteristics. J. Propul. Power 16(2000), 2, 336–339.
[4] Gholamrezaei M., Ghorbanian K.: Compressor map generation using a feedforward neural network and rig data. P.I. Mech. Eng. A: J. Power Energ. 224(2010), 1, 97–108.
[5] Tsoutsanis E., Meskin N., Benammar M., Khorasani K.: Transient gas turbine performance diagnostics through nonlinear adaptation of compressor and turbine maps. ASME J. Eng. Gas Turbines Power 137(2015), 9, 091201.
[6] Walsh P., Fletcher P.: Gas Turbine Performance. Blackwel, Bristol 2004.
[7] Sethi V., Doulgeris G., Pilidis P., Nind, A., Doussinault M., Cobas P., Rueda A.: The map fitting tool methodology: gas turbine compressor off-design performance modeling. ASME J. Turbomach. 135(2013), 6, 061010.
[8] Kurzke J.: How to get component maps for aircraft gas turbine performance calculations. Proc. ASME 1996 Int. Gas Turbine and Aeroengine Cong. Exhibit., Vol. 5, Birmingham, June 10–13, 1996, V005T16A0011996. ASME Pap. 96-GT-164.
[9] Misté G., Benini E.: Improvements in off design aeroengine performance prediction using analytic compressor map interpolation. Int. J. Turbo Jet Eng. 29(2012), 69–77.
[10] Muszynski M., Orkisz M.: Turbine Jet Engine Modelling. Ser. Scientific Library 7, Institute of Aviation, Warszawa 1997 (in Polish).
[11] Jones G., Pilidis P., Curnock B.: Extrapolation of Compressor Characteristics to the Low-Speed Region for Sub-Idle Performance Modelling. Proc. ASME Turbo Expo 2002, Power for Land, Sea, and Air, Vol, 2, Turbo Expo 2002, Pts., A, B, Amsterdam, June 3–6, 2002, 861–867. ASME Pap. GT2002–30649.
[12] De-You Y., Zhong-Fan M.: A dynamic model of turbojet in starting at high altitude. AIAA Pap. 83–7045, 1983.
[13] Jensen J., Kristensen A., Sorenson S., Houbak N. Hendricks E.: Mean value modeling of a small turbocharged diesel engine. SAE Tech. Pap. 910070, 1991.
[14] Tsoutsanis E., Meskin N., Benammar M., Khorasani K.: A component map tuning method for performance prediction and diagnostics of gas turbine compressors. Appl. Energ. 135(2014), 572–585.
[15] Tsoutsanis E., Meskin N., Benammar M., Khorasani K.: An Efficient Component Map Generation Method for Prediction of Gas Turbine Performance. Proc. ASME Turbo Expo 2014, Turbine Technical Conference and Exposition, Vol. 6, Düsseldorf, June 16–20, 2014, V006T06A006, ASME Pap. GT2014–25753.
[16] Trawinski P.: Development of flow and efficiency characteristics of an axial compressor with an analytical method including cooling air extraction and variable inlet guide vane angle. Arch. Thermodyn. 42(2021), 4, 17–46.
[17] Converse G.L., Giffen R.G.: Representation of Compressor Fans and Turbines. Vol. 1. CMGEN User’s Manual, NASA-CR-174645, 1984.
[18] Kong C., Ki J., Kang M.: A new scaling method for component maps of gas turbine using system identification. ASME J. Eng. Gas Turbines Power 125(2003), 4, 979–985.
[19] Kong C., Kho S., Ki J.: Component map generation of a gas turbine using genetic algorithms. ASME J. Eng. Gas Turbines Power 128(2006), 1, 92–96.
[20] Kong C., Ki J., Lee C.: Components map generation of gas turbine engine using genetic algorithms and engine performance deck data. Proc. ASME Turbo Expo 2006, Power for Land, Sea, and Air, Vol. 4, Barcelona, May 8–11, 2006, 377–383. ASME Pap. GT2006–90975.
[21] Zagorowska M., Thornhill N.: Compressor map approximation using Chebyshev polynominals. In: Proc. IEEE 2017, 25th Mediterranean Conf. on Control and Automation, Valletta, July 3–6, 2017, 864–869.
[22] Li X., Yang C., Wang Y., Wang H., Zu X., Sun Y., Hu S.: Compressor map regression modelling based on partial least squares. R. Soc. Open Sci. 5(2018), 8, 172454.
[23] Ghorbanian K., Gholamrezaei Mohammad.: An artificial neural network approach to compressor performance prediction. Appl. Energ. 86(2009), 1210–1221.
[24] Ghorbanian K, Gholamrezaei M.: Axial compressor performance map prediction using artificial neural network. Proc. ASME Turbo Expo 2007, Power for Land, Sea, and Air, Vol. 6, Turbo Expo 2007, Pts. A, B, Montreal, May 14-17, 2007, 1199–1208, ASME Pap. GT2007–27165.
[25] Youhong Y., Lingen Ch., Fengrui S., Chih W.: Neural-network based analysis and prediction of a compressor’s characteristic performance map. Appl. Energ. 84(2007), 1, 48–55.
[26] Hornik K., Stinchcombe M., White H.: Multilayer feedforward networks are universal approximators. Neural Networks 2(1989), 5, 359–366.
[27] Pinkus A.: Approximation theory of the MLP model in neural networks. Acta Numerica, 8(1999), 143–195.
[28] Hagan M.T., Demuth H.B., Jesús O.D.: An introduction to the use of neural networks in control systems. Int. J. Robust Nonlin. Contr. 12(2002), 959–985.
[29] www.mathworks.com/help/deeplearning/ref/neuralnetfitting-app.html (accessed 17 Apr. 2021).
[30] Hagan M.T., Menhaj M.B.: Training feedforward networks with the Marquardt algorithm. IEEE T. Neural Netw. 5(1994), 6, 989–993.
[31] Burden F., Winkler D.: Bayesian regularization of neural networks. In: Artificial Neural Networks), ser. Methods in Molecular Biology Vol. 458 (D.J. Livingstone, Eds.). Humana Press, 2008.
Go to article

Authors and Affiliations

Sergiusz Michał Loryś
1
Marek Orkisz
2

  1. Hamilton Sundstrand Poland / Pratt & Whitney AeroPower Rzeszów, Hetmanska 120, 35-078 Rzeszów, Poland
  2. Rzeszow University of Technology, Department of Aerospace Engineering, Powstanców Warszawy 8, 35-959 Rzeszów, Poland
Download PDF Download RIS Download Bibtex

Abstract

To better extract feature maps from low-resolution (LR) images and recover high-frequency information in the high-resolution (HR) images in image super-resolution (SR), we propose in this paper a new SR algorithm based on a deep convolutional neural network (CNN). The network structure is composed of the feature extraction part and the reconstruction part. The extraction network extracts the feature maps of LR images and uses the sub-pixel convolutional neural network as the up-sampling operator. Skip connection, densely connected neural networks and feature map fusion are used to extract information from hierarchical feature maps at the end of the network, which can effectively reduce the dimension of the feature maps. In the reconstruction network, we add a 3×3 convolution layer based on the original sub-pixel convolution layer, which can allow the reconstruction network to have better nonlinear mapping ability. The experiments show that the algorithm results in a significant improvement in PSNR, SSIM, and human visual effects as compared with some state-of-the-art algorithms based on deep learning.
Go to article

Authors and Affiliations

Xin Yang
1
Yifan Zhang
1
Dake Zhou
1

  1. College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, 210016 Nanjing, Jiangsu, China
Download PDF Download RIS Download Bibtex

Abstract

Prior any satellite technology developments, the geodetic networks of a country were realized from a topocentric datum, and hence the respective cartography was performed. With availability of Global Navigation Satellite Systems-GNSS, cartography needs to be updated and referenced to a geocentric datum to be compatible with this technology. Cartography in Ecuador has been performed using the PSAD56 (Provisional South American Datum 1956) systems, nevertheless it’s necessary to have inside the system SIRGAS (SIstema de Referencia Geocéntrico para las AmericaS). This transformation between PSAD56 to SIRGAS use seven transformation parameters calculated with the method Helmert. These parameters, in case of Ecuador are compatible for scales of 1:25 000 or less, that does not satisfy the requirements on applications for major scales. In this study, the technique of neural networks is demonstrated as an alternative for improving the processing of UTM planes coordinates E, N (East, North) from PSAD56 to SIRGAS. Therefore, from the coordinates E, N, of the two systems, four transformation parameters were calculated (two of translation, one of rotation, and one scale difference) using the technique bidimensional transformation. Additionally, the same coordinates were used to training Multilayer Artificial Neural Network -MANN, in which the inputs are the coordinates E, N in PSAD56 and output are the coordinates E, N in SIRGAS. Both the two-dimensional transformation and ANN were used as control points to determine the differences between the mentioned methods. The results imply that, the coordinates transformation obtained with the artificial neural network multilayer trained have been improving the results that the bidimensional transformation, and compatible to scales 1:5000.
Go to article

Authors and Affiliations

Alfonso Tierra
Ricardo Romero
Download PDF Download RIS Download Bibtex

Abstract


Analysis of lead and cadmium concentrations in the air comparing concentration values difference between heating and summer seasons was carried out in the paper. Relevant procedure was adopted to find out if the concentration values in these two seasons differed in kind. The concentration seasonal difference was not found in case of cadmium but it was found for lead. It was proved in further part of the paper that the analysed mean 24-hour Pb concentrations for heating season could be presented as a sum of the mean annual background concentration and the concentration values resulted from Pb emission from sources active only in the heating season. In the area where the measurements were carried out residential furnaces were this kind of sources. The cumulative distribution function of the mean 24-hour lead concentration resulted from Pb emissions in the heating season was determined using two-layer neural network. It was found according to this approach that Pb concentration as the result of Pb emissions from residential furnaces, for 145 days, i.e. 80% of the heating season period, were at least two-fold lower than the lead concentration values as the result of Pb emission from the all year active sources. Only for 14 days emission sources active in the heating season produced Pb concentrations higher than Pb mean annual background concentration.
Go to article

Authors and Affiliations

Czesław Kliś
Stanisław Hławiczka
Download PDF Download RIS Download Bibtex

Abstract

Noise control has gained a lot of attention recently. However, presence of nonlinearities in signal paths for some applications can cause significant difficulties in the operation of control algorithms. In particular, this problem is common in structural noise control, which uses a piezoelectric shunt circuit. Not only vibrating structures may exhibit nonlinear characteristics, but also piezoelectric actuators. In this paper, active device casing is addressed. The objective is to minimize the noise coming out of the casing, by controlling vibration of its walls. The shunt technology is applied. The proposed control algorithm is based on algorithms from a group of soft computing. It is verified by means of simulations using data acquired from a real object.

Go to article

Authors and Affiliations

Sebastian Kurczyk
Marek Pawełczyk
Download PDF Download RIS Download Bibtex

Abstract

This study investigates the estimated adsorption efficiency of artificial Nickel (II) ions with perlite in an aqueous solution using artificial neural networks, based on 140 experimental data sets. Prediction using artificial neural networks is performed by enhancing the adsorption efficiency with the use of Nickel (II) ions, with the initial concentrations ranging from 0.1 mg/L to 10 mg/L, the adsorbent dosage ranging from 0.1 mg to 2 mg, and the varying time of effect ranging from 5 to 30 mins. This study presents an artificial neural network that predicts the adsorption efficiency of Nickel (II) ions with perlite. The best algorithm is determined as a quasi-Newton back-propagation algorithm. The performance of the artificial neural network is determined by coefficient determination (R2), and its architecture is 3-12-1. The prediction shows that there is an outstanding relationship between the experimental data and the predicted values.

Go to article

Authors and Affiliations

Sinan Mehmet Turp
Download PDF Download RIS Download Bibtex

Abstract

Since a few years ago, there is an increasing interest for utilization of transfer functions (TF) as a reliable method for diagnosing of mechanical faults in transformer structure. However, this paper aims to develop the application of TF method in order to evaluate the drying quality of active part during the manufacturing process of transformer. To reach this goal, the required measurements are carried out on 50 MVA 132 KV/33 KV power transformer when active part is placed in the drying chamber. Two different features extracted from the measured TFs are then used as the inputs to artificial neural network (ANN) to give an estimate for required time in drying process. Results show that this new represented method could well forecast the required time. The results obtained from this method are valid for all the transformers which have the same design.

Go to article

Authors and Affiliations

Hormatollah Firoozi
Mehdi Bigdeli
Download PDF Download RIS Download Bibtex

Abstract

The article presents results of the influence of the GMDH (Group Method of Data Handling) neural network input data preparation method on the results of predicting corrections for the Polish timescale UTC(PL). Prediction of corrections was carried out using two methods, time series analysis and regression. As appropriate to these methods, the input data was prepared based on two time series, ts1 and ts2. The implemented research concerned the designation of the prediction errors on certain days of the forecast and the influence of the quantity of data on the prediction error. The obtained results indicate that in the case of the GMDH neural network the best quality of forecasting for UTC(PL) can be obtained using the time-series analysis method. The prediction errors obtained did not exceed the value of ± 8 ns, which confirms the possibility of maintaining the Polish timescale at a high level of compliance with the UTC.

Go to article

Authors and Affiliations

Wiesław Miczulski
Łukasz Sobolewski
Download PDF Download RIS Download Bibtex

Abstract

The aim of this paper is to answer the question: Are the Łódź Hills useful for electrical energy production from wind energy or not? Due to access to short-term data related to wind measurements (the period of 2008 and 2009) from a local meteorological station, the measure – correlate – predict approach have been applied. Long-term (1979‒2016) reference data were obtained from ECWMF
ERA-40 Reanalysis. Artificial neural networks were used to calculate predicted wind speed. The obtained average wind speed and wind power density was 4.21 ms⁻¹ and 70 Wm⁻¹, respectively, at 10 m above ground level (5.51 ms⁻¹, 170 Wm⁻¹ at 50 m). From the point of view of Polish wind conditions, Łódź Hills may be considered useful for wind power engineering.

Go to article

Authors and Affiliations

R. Korupczyński
J. Trajer
Download PDF Download RIS Download Bibtex

Abstract

The article shows a new model of Continuous Cooling Transformation (CCT) diagrams of structural steels and engineering steels. The modelling used artificial neural networks and a set of experimental data prepared based on 550 CCT diagrams published in the literature. The model of CCT diagrams forms 17 artificial neural networks which solve classification and regression tasks. Neural model is implemented in a computer software that enables calculation of a CCT diagram based on chemical composition of steel and its austenitizing temperature.

Go to article

Authors and Affiliations

J. Trzaska
Download PDF Download RIS Download Bibtex

Abstract

Due to fast-paced technical development, companies are forced to modernise and update

their equipment, as well as production planning methods. In the ordering process, the customer

is interested not only in product specifications, but also in the manufacturing lead

time by which the product will be completed. Therefore, companies strive towards setting

an appealing but attainable manufacturing lead date.

Manufacturing lead time depends on many different factors; therefore, it is difficult to predict.

Estimation of manufacturing lead time is usually based on previous experience. In the

following research, manufacturing lead time for tools for aluminium extrusion was estimated

with Artificial Intelligence, more precisely, with Neural Networks.

The research is based on the following input data; number of cavities, tool type, tool category,

order type, number of orders in the last 3 days and tool diameter; while the only output

data are the number of working days that are needed to manufacture the tool. An Artificial

Neural Network (feed-forward neural network) was noted as a sufficiently accurate method

and, therefore, appropriate for implementation in the company.

Go to article

Authors and Affiliations

Nika Sajko
Simon Kovacic
Mirko Ficko
Iztok Palcic
Simon Klancnik
Download PDF Download RIS Download Bibtex

Abstract

The paper addresses the problem of solving overdetermined systems of linear equations by means of methods of robust estimations, which eliminate the effect of outliers on the estimation results. The process of estimating a vector of parameters was accomplished by means of circular in structure neural networks. Formulating the problem in the aspect of a method for estimating parameters requires formulating an energy function (objective function) whose form was modified by means of a determined weighting function. In the final part of the paper the effectiveness of the methods described was evaluated in terms of controlling and diagnosing a geodetic observation system. The article is merely an introduction to a broadly understood problem of geodetic uses of robust estimators.
Go to article

Authors and Affiliations

Józef Gil
Download PDF Download RIS Download Bibtex

Abstract

The sedimentation devices are commonly used in the clarifying of industrial suspensions and in the civil engineering. The sedimentation efficiency plays very important role in the environmental protection. The aim of the research was to investigate the possibilities of applying neural networks in computing the efficiency of sedimentation processes. Input data were the results of computer stimulation performed according to the mathematical model taking into account the overflow rate in the sedimentation facilities and physical parameters of the suspension, such as probability density function of solid particle size. Two probability density functions of solid particle size were compared: log-normal distribution and gamma distribution. Feed-forward neural networks (with no feedback and with one- stream flow of information) were applied in research work. Teacher-supervised teaching, according to back-propagation method with the use of Levenberg-Marquardt algorithm, was chosen. When neural networks were taught with the use of sets including less than 400 data elements, the errors were more than I%. Neural networks taught by means of series including more than 500 data sets would yield acceptable results and the error was less than I%. Accordingly, one can presume that the smallest teaching set is the one composed of 500 data elements. The best results were obtained when the number of data sets was about 5000- the differences in computed sedimentation efficiency were then less than 0.5%. A further increase in the number of data elements - above 5000 - would lead to lower accuracy of calculations.
Go to article

Authors and Affiliations

Włodzimierz P. Kowalski
Krzysztof Kołodziejczyk
Tomasz Zacharz
Download PDF Download RIS Download Bibtex

Abstract

A smart control based on neural networks for multicellular converters has been developed and implemented. The approach is based on a behavioral description of the different converter operating modes. Each operating mode represents a well-defined configuration for which an operating zone satisfying given invariance conditions, depending on the capacitors’ voltages and the load current of the converter, is assigned. A control vector, whose components are the control signals to be applied to the converter switches is generated for each mode. Therefore, generating the control signals becomes a classification task of the different operating zones. For this purpose, a neural approach has been developed and implemented to control a 2-cell converter then extended to a 3-cell converter. The developed approach has been compared to super-twisting sliding mode algorithm. The obtained results demonstrate the approach effectiveness to provide an efficient and robust control of the load current and ensure the balancing of the capacitors voltages.
Go to article

Bibliography

[1] Benmansour K., Réalisation d’un banc d’essai pour la Commande et l’Observation des Convertisseurs Multicellulaires séries, Approche Hybride, PhD Thesis, Université de Cergy Pontoise, France (2009).
[2] Colak I., Kabalci E., Bayindira R., Review of multilevel voltage source inverter topologies and control schemes, Energy Conversion and Management Journal, vol. 52, iss. 2, pp. 1114–1128 (2011).
[3] Laidi K., Benmansour K., Ferdjouni A., Bouchhida O., Real-time implementation of an interconnected observer design for p-cells chopper, Archives of Electrical Engineering, vol. 59, no. 2, pp. 5–20 (2010).
[4] Meynard T., Foch H., Multilevel choppers for high voltage applications, European Power Electronics and Drives Journal, vol. 2, no. 1, pp. 45–50 (1992).
[5] Meynard T., Foch H., Electronic device for electrical energy conversion between a voltage source and a current source by means of controllable switching cells, European Patent 92/91 6336.8 (1992).
[6] Laidi K., Benmansour K., High Order Sliding Mode Controller of Mid-point Multi-cellular Converter, 2nd International Symposium on Friendly Energy and Applications, Newcastle Upon Tyne, pp. 493–498 (2012).
[7] Pinon D., Commande des Convertisseurs Multicellulaires par Mode de Glissement, PhD Thesis, INPT, Toulouse (2000).
[8] Skender M.R., Tlemçani A., A New Algorithme Observer of Higher Order Sliding Mode Applied to Serial Multicell Converter, Revue Roumaine des Sciences Techniques – Série Électrotechnique et Énergétique, vol. 61, no. 2, pp. 126–130 (2016).
[9] Zhang H., Dong H., Zhang B., Tong Wu, Changwen Chen, Research on beam supply control strategy based on sliding mode control, Archives of Electrical Engineering, vol. 69, no 2, pp. 349–364 (2020).
[10] Amet L., Ghanes M., Barbot J.P., Direct control based on sliding mode techniques for multicells serial chopper, American Control Conference, San Francisco, CA, USA (2011).
[11] Laamiri S., Ghanes M., Amet L., Santomenna.G, Direct Control Strategy for a Three Phase Eight-Level Flying-Capacitor Inverter, IFAC Journal of Systems and Control, vol. 50, iss. 1, pp. 15786–15791 (2017).
[12] Benzineb O., Taibi F., Benbouzid M.E., Boucherit M.S., Tadjine M., Multicell Converters Hybrid Sliding Mode Control, IFAC World Congress 2014, Cape Town, South Africa, pp. 11659–11666 (2014).
[13] Bensaid S., Bensaad K., Benrejeb M., On Two Control Strategies for Multicellular Converters, International Journal of Control, Energy and Electrical Engineering (CEEE), vol. 1, pp. 37–42 (2014).
[14] Djondine P., Barbot J.P., Ghanes M., Comparison of sliding mode and petri nets control for multicellular chopper, International Journal of Nonlinear Science, vol. 25, no. 2, pp. 67–75 (2018).
[15] Salinas S., Ghanes M., Barbot J.P., Escalante F., Amghar B., Modeling and Control Design Based on Petri Nets for Serial Multicellular Choppers, IEEE Transactions on Control Systems Technology, vol. 23, no. 1 (2015).
[16] Derugo P., Zychlewicz M., Reproduction of the control plane as a method of selection of settings for an adaptive fuzzy controller with Petri layer, Archives of Electrical Engineering, vol. 69, no. 3, pp. 609–624 (2020).
[17] Manon P., Valentin C.R., Gilles G., Optimal Control of Hybrid Dynamical Systems: Application in Process Engineering, Control Engineering Practice, pp. 133–149 (2002).
[18] Teel A.R., Bonivento C., Isidori A., Marconi L., Rossi C., Robust hybrid control systems: an overview of some recent results, Advances in Control Theory and Applications, Springer, vol. 353, pp. 279–302 (2007).

Go to article

Authors and Affiliations

Kamel Laidi
1
Ouahid Bouchhida
1
Mokhtar Nibouche
2
Khelifa Benmansour
1

  1. University of Medea, Algeria
  2. University of the West of England, United Kingdom
Download PDF Download RIS Download Bibtex

Abstract

The Convolutional Neural Network (CNN) model is one of the most effective models for load forecasting with hyperparameters which can be used not only to determine the CNN structure and but also to train the CNN model. This paper proposes a framework for Grid Search hyperparameters of the CNN model. In a training process, the optimal models will specify conditions that satisfy requirement for minimum of accuracy scores of Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE). In the testing process, these optimal models will be used to evaluate the results along with all other ones. The results indicated that the optimal models have accuracy scores near the minimum values. Load demand data of Queensland (Australia) and Ho Chi Minh City (Vietnam) were utilized to verify the accuracy and reliability of the Grid Search framework.
Go to article

Bibliography

[1] Walther J., Spanier D., Panten N., Abele E., Very short-term load forecasting on factory level – A machine learning approach, Procedia CIRP, vol. 80, pp. 705–710 (2019).
[2] Aydarous A.A., Elshahed M.A., Hassan M.M.A., Short-Term Load Forecasting Approach Based on Different Input Methods of One Variable: Conceptual and Validation Study, 2018 Twentieth International Middle East Power Systems Conference (MEPCON), Cairo, Egypt, pp. 179–184 (2018).
[3] Raza M.Q., Khosravi A., A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings, Renew. Sustain. Energy Rev., vol. 50, pp. 1352–1372 (2015).
[4] Walther J., Spanier D., Panten N., Abele E., Very short-term load forecasting on factory level – A machine learning approach, Procedia CIRP, vol. 80, pp. 705–710 (2019).
[5] Khan S., Javaid N., Chand A., Abbasi R.A., Khan A.B.M., Faisal H.M., Forecasting day, week and month ahead electricity load consumption of a building using empirical mode decomposition and extreme learning machine, 2019 15th InternationalWireless Communications and Mobile Computing Conference (IWCMC), Tangier, Morocco, pp. 1600–1605 (2019).
[6] Joshi M., Singh R., Short-term load forecasting approaches: A review, International Journal of Recent Engineering Research and Development (IJRERD), no. 01, pp. 9–17 (2015).
[7] Cao Z., Member S., Wan C., Zhang Z., Hybrid Ensemble Deep Learning for Deterministic and Probabilistic Low-voltage Load Forecasting, IEEE Trans. Power Syst., p. 1 (2019).
[8] Yu Y., Ji T.Y., Li M.S., Wu Q.H., Short-term Load Forecasting Using Deep Belief Network with Empirical Mode Decomposition and Local Predictor, 2018 IEEE Power and Energy Society General Meeting (PESGM), Portland, OR, pp. 1–5 (2018).
[9] Yang J.,Wang Q., A Deep Learning Load Forecasting Method Based on Load Type Recognition, 2018 International Conference on Machine Learning and Cybernetics (ICMLC), Chengdu, pp. 173–177 (2018).
[10] Krishnakumari K., Sivasankar E., Radhakrishnan S., Hyperparameter tuning in convolutional neural networks for domain adaptation in sentiment classification (HTCNN-DASC), Soft Comput., vol. 24, no. 5, pp. 3511–3527 (2020).
[11] Subramanian S.V., Rao A.H., Deep-learning based time series forecasting of go-around incidents in the national airspace system, AIAA Model. Simul. Technol. Conf. 2018, no. 209959 (2018).
[12] Zahid M. et al., Electricity price and load forecasting using enhanced convolutional neural network and enhanced support vector regression in smart grids, Electronics, vol. 8, no. 2, pp. 1–32 (2019).
[13] Nurshazlyn Mohd Aszemi, Dhanapal Durai Dominic Panneer Selvam, Hyperparameter optimization in convolutional neural network using genetic algorithms, Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 6, pp. 269–278 (2019).
[14] Brownlee J., Deep Learning for Time Series Forecasting, Ebook (2019).
[15] https://keras.io/optimizers/
[16] Brownlee J., Deep Learning with Python, Ebook (2019).
[17] Chen K., Chen K., Wang Q., He Z., Hu J., He J., Short-Term Load Forecasting With Deep Residual Networks, IEEE Transactions on Smart Grid, vol. 10, no. 4, pp. 3943–3952 (2019).
[18] Jojo Moolayil, Learn Keras for Deep Neural Networks: A Fast-Track Approach to Modern Deep Learning with Python, Apress (2018).
[19] Xishuang Dong, Lijun Qian, Lei Huang, Short-term load forecasting in smart grid: A combined CNN and K-means clustering approach, IEEE Int. Conf. Big Data Smart Comput., pp. 119–125 (2017).
[20] Dong X., Qian L., Huang L., A CNN based bagging learning approach to short-term load forecasting in smart grid, 2017 SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI, San Francisco, CA, 2017, pp. 1–6 (2017).
[21] Voß M., Bender-Saebelkampf C., Albayrak S., Residential Short-Term Load Forecasting Using Convolutional Neural Networks, 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Aalborg, 2018, pp. 1–6 (2018).
[22] Amarasinghe K., Marino D.L., Manic M., Deep neural networks for energy load forecasting, IEEE Int. Symp. Ind. Electron., pp. 1483–1488 (2017).
[23] Koprinska I., Wu D., Wang Z., Convolutional Neural Networks for Energy Time Series Forecasting, Proc. Int. Jt. Conf. Neural Networks, pp. 1–8 (2018), DOI: 10.1109/IJCNN.2018.8489399.
[24] Valentino Zocca et al., Python Deep Learning, Packt Publishing (2019).
[25] https://www.aemo.com.au/
[26] Haiqing Liu, Weijian Lin, Yuancheng Li, Ultra-short-term wind power prediction based on copula function and bivariate EMD decomposition algorithm, Archives of Electrical Engineering, vol. 69, no. 2, pp. 271–286 (2020).
[27] Wang Y., Ma X., Wang F., Hou X., Sun H., Zheng K., Dynamic electric vehicles charging load allocation strategy for residential area, Archives of Electrical Engineering, vol. 67, no. 3, pp. 641–654 (2018).
Go to article

Authors and Affiliations

Thanh Ngoc Tran
1

  1. Faculty of Electrical Engineering Technology, Industrial University of Ho Chi Minh City, 12 Nguyen Van Bao, Ward 4, Go Vap District, Ho Chi Minh City, Vietnam
Download PDF Download RIS Download Bibtex

Abstract

To improve the user’s localization estimation in indoor and outdoor environment a novel radiolocalization system using deep learning dedicated to work both in indoor and outdoor environment is proposed. It is based on the radio signatures using radio signals of opportunity from LTE an WiFi networks. The measurements of channel state estimators from LTE network and from WiFi network are taken by using the developed application. The user’s position is calculated with a trained neural network system’s models. Additionally the influence of various number of measurements from LTE and WiFi networks in the input vector on the positioning accuracy was examined. From the results it can be seen that using hybrid deep learning algorithm with a radio signatures method can result in localization error 24.3 m and 1.9 m lower comparing respectively to the GPS system and standalone deep learning algorithm with a radio signatures method in indoor environment. What is more, the combination of LTE and WiFi signals measurement in an input vector results in better indoor and outdoor as well as floor classification accuracy and less positioning error comparing to the input vector consisting measurements from only LTE network or from only WiFi network.
Go to article

Authors and Affiliations

Sebastian Urwan
1
Dominika R. Wysocka
1
Alicja Pietrzak
1
Krzysztof K. Cwalina
1

  1. Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, 80-233 Gdansk, Poland
Download PDF Download RIS Download Bibtex

Abstract

In modern conditions in the field of medicine, raster image analysis systems are becoming more widespread, which allow automating the process of establishing a diagnosis based on the results of instrumental monitoring of a patient. One of the most important stages of such an analysis is the detection of the mask of the object to be recognized on the image. It is shown that under the conditions of a multivariate and multifactorial task of analyzing medical images, the most promising are neural network tools for extracting masks. It has also been determined that the known detection tools are highly specialized and not sufficiently adapted to the variability of the conditions of use, which necessitates the construction of an effective neural network model adapted to the definition of a mask on medical images. An approach is proposed to determine the most effective type of neural network model, which provides for expert evaluation of the effectiveness of acceptable types of models and conducting computer experiments to make a final decision. It is shown that to evaluate the effectiveness of a neural network model, it is possible to use the Intersection over Union and Dice Loss metrics. The proposed solutions were verified by isolating the brachial plexus of nerve fibers on grayscale images presented in the public Ultrasound Nerve Segmentation database. The expediency of using neural network models U-Net, YOLOv4 and PSPNet was determined by expert evaluation, and with the help of computer experiments, it was proved that U-Net is the most effective in terms of Intersection over Union and Dice Loss, which provides a detection accuracy of about 0.89. Also, the analysis of the results of the experiments showed the need to improve the mathematical apparatus, which is used to calculate the mask detection indicators.
Go to article

Authors and Affiliations

I. Tereikovskyi
1
Oleksandr Korchenko
S. Bushuyev
2
O. Tereikovskyi
3
Ruslana Ziubina
Olga Veselska

  1. Department of System Programming and Specialised Computer Systems of the National Technical University of Ukraine, Igor Sikorsky Kyiv Polytechnic Institute, Ukraine
  2. Department of Project Management Kyiv National University of Construction and Architecture, Ukraine
  3. Department of Information Technology Security of National Aviation University, Kyiv, Ukraine
Download PDF Download RIS Download Bibtex

Abstract

Effective recognition of tags in the dynamic measurement system would significantly improve the reading performance of the tag group, but the blurred outline and appearance of tag images captured in motion seriously limit the effectiveness of the existing tag group recognition. Thus, this paper proposes passive tag group recognition in the dynamic environment based on motion blur estimation and improved YOLOv2. Firstly, blur angles are estimated with a Gabor filter, and blur lengths are estimated through nonlinear modelling of a Generalized Regression Neural Network (GRNN). Secondly, tag recognition based on YOLOv2 improved by a Gaussian algorithm is proposed. The features of the tag group are analyzed by the Gaussian algorithm, the region of interest of the dynamic tag is effectively framed, and the tag foreground is extracted; Secondly, the data set of tag groups are trained by the end-to-end YOLOv2 algorithm for secondary screening and recognition, and finally the specific locations of tags are framed to meet the effective identification of tag groups in different scenes. A considerable number of experiments illustrate that the fusion algorithm can significantly improve recognition accuracy. Combined with the reading distance, the research presented in this paper can more accurately optimize the three-dimensional structure of the tag group, improve the reading performance of the tag group, and avoid the interference and collision of tags in the communication channel. Compared with the previous template matching algorithm, the tag group recognition ability put forward in this paper is improved by at least 13.9%, and its reading performance is improved by at least 6.2% as shown in many experiments.
Go to article

Authors and Affiliations

Lin Li
1 2
Xiao-Lei Yu
1 2
Zhen-Lu Liu
1
Zhi-Min Zhao
1
Ke Zhang
1
Shan-Hao Zhou
1

  1. College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
  2. National Quality Supervision and Testing Center for RFID Product Jiangsu, Nanjing 210029, China
Download PDF Download RIS Download Bibtex

Abstract

Aiming at the problems of delay and couple in the sintering temperature control system of lithium batteries, a fuzzy neural network controller that can solve complex nonlinear temperature control is designed in this paper. The influence of heating voltage, air inlet speed and air inlet volume on the control of temperature of lithium battery sintering is analyzed, and a fuzzy control system by using MATLAB toolbox is established. And on this basis, a fuzzy neural network controller is designed, and then a PID control system and a fuzzy neural network control system are established through SIMULINK. The simulation shows that the response time of the fuzzy neural network control system compared with the PID control system is shortened by 24s, the system stability adjustment time is shortened by 160s, and the maximum overshoot is reduced by 6.1%. The research results show that the fuzzy neural network control system can not only realize the adjustment of lithium battery sintering temperature control faster, but also has strong adaptability, fault tolerance and anti-interference ability.
Go to article

Bibliography

[1] Li, H.S., Miao, Q. & Zhou, R.M. (2014). Research on control algorithm of ceramic kiln temperature control system. Journal of Wuhan University of Technology. 36(10), 135-139. DOI: 10.3963/j.issn.1671-4431.2014.10.024.
[2] Zhu, D.Q. & Jiang, K.R. (2009). Design and simulation of fuzzy neural network controller for drying process. Journal of System Simulation. 21(15), 4768-4771. DOI: 10.16182/j.cnki.joss.2009.15.079.
[3] Zhang, Z.M., Zhang, J.Y. & Feng, X.G. (2019). Design of hot blast stove temperature control system based on RBF neural network tuning. Journal of Hebei University of Science and Technology. 40(06), 503-511. DOI: 10.7535/hbkd.2019yx06007.
[4] Bai, G.Z. & Yu, J.H. (2016). PID parameter self-tuning based on improved fuzzy neural network. Computer Application Research. 33(11), 3358-3363+3368. DOI: 10.3969/j.issn.1001-3695.2016.11.035.
[5] Li, C.L. & Huang, C.Z. (2010). Design of temperature control system based on fuzzy neural network. Microcomputer Information. 26(07), 75-76+98. DOI: 10.3969/j.issn.2095-6835.2010.07.031.
[6] Li, G.Q., Tong, S.H. & Lu, L.X. (2013). Analysis of the temperature field in a continuous sintering furnace for solar cells. Computer Simulation. 30(01), 188-192+218. DOI: 10.3969/j.issn.1006-9348.2013.01.043.
[7] Huang, B., Xie, G.J., Liang, W.S. & Zhang, J.W. (2018). Application of heating furnace temperature control system based on hybrid fuzzy PID. Electric Drive. 48(02), 43-46. DOI: 10.19457/j.1001-2095.20180208.
[8] Zhou, G.L., Peng, Y.F. & Dong, H.S. (2007). Design of adaptive fuzzy PID controller based on T-S model. Industrial Instrumentation and Automation. 2, 22-25. DOI: CNKI: SUN: GYZD.0.2007-02-005.
[9] Tan, M., Cheng, C.H. & Lu, C. (2006). Research on the temperature control system of vacuum sintering furnace based on neural network. Measurement and Control Technology. 2, 31-32+53. DOI: 10.19708/j.ckjs.2006.02.010.
[10] Wang, J.P. & Ku, M.S. (2010). Application of FNN on atmospheric heating furnace of distillation unit. Computer Measurement and Control. 18(11), 2649-2651. DOI: 10.16526/j.cnki.11-4762/tp.2010.11.003. [11] Chen, B.F., Yin, P.L. & Ma, L. (2010). Research on temperature control system based on fuzzy neural network. Computer and Digital Engineering. 38(07), 54-57. DOI: 10.3969/j.issn.1672-9722.2010.07.016.
[12] Li, M.H. & Li, Z.Q. (2012). Research on Decoupling Control Strategy of Injection Molding Machine Barrel Temperature Based on Neural Network. Ceramics. 4, 17-19. DOI: 10.19397/j.cnki.ceramics.2012.04.004.
[13] Hu, Y.N. & Ma, W.M. (2017). Research and application of paper quantitative moisture control strategy based on FNN decoupling. China Paper. 36(07), 48-53. DOI: 10.11980/j.issn.0254-508X.2017.07.009. [14] Zhang, L., Zhang, J.C., Han, H.G. & Qiao, J.F. (2020). Process control of biochemical phosphorus removal in sewage treatment based on fuzzy neural network. CIESC Journal. 71(03). 1217-1225. DOI: 10.11949/0438-1157.20191514.
[15] Tao, X.M., Luo, L. & Liu, Z.G. (2015). Research and simulation of injection molding machine barrel temperature control algorithm based on segmented PID. Plastics. 44(03), 68-70. DOI: CNKI: SUN: SULA.0.2015-03-022.
[16] Zhou, P.Q. (2016). Research on synchronization control technology of double winches based on fuzzy neural network. Machine Design and Manufacture. 9, 64-68. DOI: 10.19356/j.cnki.1001-3997.2016.09.017.
[17] Li, J.J., Xu, Y., Zhang, G., Wei, Z.Y. & Zhang, Y.B. (2015). Irrigation controller design based on BP neural network prediction and fuzzy control. Machine Design and Research. 31(05), 150-154. DOI: 10.13952/j.cnki.jofmdr. 2015.0207.
[18] Luo, C.N., Hao, R.K. & Yang, W. (2018). Boiler temperature control simulation in industrial production process. Computer simulation. 35(09), 358-362. DOI: 10.3969/j.issn.1006-9348.2018.09.074.
[19] Zhao, J. & Xu, H. (2016). Computer simulation study on segmental control of barrel temperature of injection molding machine. Synthetic Resin and Plastics. 33(05), 61-63. DOI: 10.3969/j.issn.1002-1396.2016.05.018.
Go to article

Authors and Affiliations

Zou Chaoxin
1
Li Rong
1
Xie Zhiping
1
Su Ming
1
Zeng Jingshi
2
Ji Xu
1
Ye Xiaoli
1
Wang Ye
1

  1. Guizhou Normal University, China
  2. Guizhou Zhenhua New Material Co., Ltd., China
Download PDF Download RIS Download Bibtex

Abstract

To address the problem that a deep neural network needs a sufficient number of training samples to have a good prediction performance, this paper firstly used the Z-Map algorithm to generate a simulated profile of the milling surface and construct an optical simulation model of surface imaging to supplement the training sample size of the neural network. Then the Deep CORAL model was used to match the textures of the simulated samples and the actual samples across domains to solve the problem that the simulated samples were not in the same domain as the actual milling samples. Experimental results have shown that high texture matching could be achieved between optical simulation images and actual images, laying the foundation for expanding the actual milled workpiece images with the simulation images. The deep convolutional neural model Xception was used to predict the classification of six classes of data sets with the inclusion of simulation images, and the accuracy was improved from 86.48% to 92.79% compared with the model without the inclusion of simulation images. The proposed method solves the problem of the need for a large number of samples for deep neural networks and lays the foundation for similar methods to predict surface roughness for different machining processes.
Go to article

Authors and Affiliations

Lingli Lu
1
Huaian Yi
1
Aihua Shu
1
Jianhua Qin
1
Enhui Lu
2

  1. School of Mechanical and Control Engineering, Guilin University of Technology, Guilin, 541006, People’s Republic of China
  2. School of Mechanical Engineering, Yangzhou University, Yangzhou, 225009, People’s Republic of China
Download PDF Download RIS Download Bibtex

Abstract

Training a neural network can be a challenging task, particularly when working with complex models and large amounts of training data, as it consumes significant time and resources. This research proposes a hybrid model that combines population-based heuristic algorithms with traditional gradient-based techniques to enhance the training process. The proposed approach involves using a dynamic population-based heuristic algorithm to identify good initial values for the neural network weight vector. This is done as an alternative to the traditional technique of starting with random weights. After several cycles of distributing search agents across the search domain, the training process continues using a gradient-based technique that starts with the best initial weight vector identified by the heuristic algorithm. Experimental analysis confirms that exploring the search domain during the training process decreases the number of cycles needed for gradient descent to train a neural network. Furthermore, a dynamic population strategy is applied during the heuristic search, with objects added and removed dynamically based on their progress. This approach yields better results compared to traditional heuristic algorithms that use the same population members throughout the search process.
Go to article

Authors and Affiliations

Amer Mirkhan
1
Numan Çelebi
2
ORCID: ORCID

  1. Sakarya University, Computer Engineering Department
  2. Sakarya University, Information Systems Engineering Department

This page uses 'cookies'. Learn more