How to search?
advanced search

Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 7
items per page: 25 50 75
Sort by:

A hybrid deep learning framework for modeling the short term global horizontal irradiance prediction of a solar power plant in India

S.V.S. Rajaprasad Rambabu Mukkamala
Polityka Energetyczna - Energy Policy Journal | 2023 | vol. 26 | No 3 | 101-116
Keywords global horizontal irradiance energy deep neural networks hybrid model
Download PDF Download RIS Download Bibtex

Abstract

The rapid development of grid integration of solar energy in developing countries like India has created vital concerns such as fluctuations and interruptions affecting grid operations. Improving the consistency and accuracy of solar energy forecasts can increase the reliability of the power grid. Although solar energy is available in abundance around the world, it is viewed as an unpredictable source due to uncertain fluctuations in climate conditions. Global horizontal irradiance (GHI) prediction is critical to efficiently manage and forecast the power output of solar power plants. However, developing an accurate GHI forecasting model is challenging due to the variability of weather conditions over time. This research aims to develop and compare univariate LSTM models capable of predicting GHI in a solar power plant in India over the short term. The present study introduces a deep neural network-based (DNN) hybrid model with a combination of convolutional neural network bi-directional long short-term memory (CNN BiLSTM) to predict the one minute interval GHI of a solar power plant located in the southern region of India. The model’s effectiveness was tested using data for the month of January 2023. In addition, the results of the hybrid model were compared to the long short-term memory (LSTM) and BiLSTM deep-learning (DL) models. It has been observed that the proposed hybrid model framework is more accurate compared to the LSTM and BiLSTM architectures. Finally, a GHI prediction tool was developed to understand the trend of the results.
Go to article

Authors and Affiliations

S.V.S. Rajaprasad
1
ORCID: ORCID
Rambabu Mukkamala
1
ORCID: ORCID
  1. National Institute of Construction Management and Research (NICMAR), Hyderabad,Telangana, India

Electric arc models with non-zero residual conductance and with increased energy dissipation

Antoni Sawicki
Archives of Electrical Engineering | 2021 | vol. 70 | No 4 | 819-834 | DOI: 10.24425/aee.2021.138263
Keywords Cassie model electric arc hybrid model Mayr model
Download PDF Download RIS Download Bibtex

Abstract

This paper describes modifications of the Mayr and Cassie models of the electric arc. They include the phenomena of increased heat dissipation and non-zero residual conductance when the current passes through zero. The modified models are combined into a new hybrid model connecting them in parallel and activated by a weight function. Two cases of functional dependence of models on current intensity and instantaneous conductance are considered. Mathematical models in differential and integral forms are presented. On their basis, computer macromodels are created and simulations of processes in circuits with arc models are performed. The families of static and dynamic arc voltage and current characteristics are presented.
Go to article

Bibliography

[1] King-Jet Tseng,YaomingWang D., MahindaVilathgamuwa, An experimentally verified hybrid Cassie- Mayr electric arc model for power electronics simulations, IEEE Transactions on Power Electronics, vol. 12, no. 3, pp. 429–436 (1997), DOI: 10.1109/63.575670.
[2] Sawicki A., Haltof M., Spectral and integral methods of determining parameters in selected electric arc models with a forced sinusoid current circuit, Archives of Electrical Engineering, vol. 65, no. 1, pp. 87–103 (2016), DOI: 10.1515/aee-2016-0007.
[3] Pentegov I.V., Sidorec V.N., Comparative analysis of models of dynamic welding arc, The Paton Welding Journal, no. 12, pp. 45–48 (2015), DOI: 10.15407/tpwj2015.12.09.
[4] Kalasek V., Measurements of time constants on cascade d.c. arc in nitrogen, TH-Report 71-E18, Eindhoven, pp. 1–30 (1971).
[5] Sawicki A., The universal Mayr–Pentegov model of the electric arc, Przegl˛ad Elektrotechniczny (Electrical Review), vol. 94, no. 12, pp. 208–211 (2019), DOI: 10.15199/48.2019.12.47.
[6] Katsaounis A., Heat flow and arc efficiency at high pressures in argon and helium tungsten arcs, Welding Research Supplement I, September, pp. 447-s–454-s (1993).
[7] Maximov S., Venegas V., Guardado J.L., Melgoza E., Torres D., Asymptotic methods for calculating electric arc model parameters, Electrical Engineering, vol. 94, no. 2, pp. 89–96 (2012), DOI: 10.1007/s00202-011-0214-6.
[8] Sawicki A., Arc models for simulating processes in circuits with a SF6 circuit breaker, Archives of Electrical Engineering, vol. 68, no. 1, pp. 147–159 (2019), DOI: 10.24425/aee.2019.125986.
[9] Sawicki A., Classical and Modified Mathematical Models of Electric Arc, Institute ofWelding Bulletin, no. 4, pp. 67–73 (2019), DOI: 10.17729/ebis.2019.4/7.
[10] Janowski T., Jaroszynski L., Stryczewska H.D., Modification of the Mayr’s electric arc model for gliding Arc Analysis, XXVI International Conference on Phenomena in Ionized Gases, Nagoya, Japan 2001/7/17, pp. 341–342 (2001).
[11] Ziani A., Moulai H., Hybrid model of electric arcs in high voltage circuit breakers, Electric Power Systems Research, vol. 92, pp. 37–42 (2012), DOI: 10.1016/j.epsr.2012.04.021.
Go to article

Authors and Affiliations

Antoni Sawicki
1
ORCID: ORCID
  1. Association of Polish Electrical Engineers (NOT-SEP), Czestochowa Division, Poland

Hybrid Predictions of the Homogenous Properties’ Market Value with the Use of Ann

Hubert Anysz Monika Podwórna Nabi Ibadov Kunibert Lennerts Kostiantyn Dikarev
Archives of Civil Engineering | 2021 | vol. 67 | No 1 | 285-301 | DOI: 10.24425/ace.2021.136474
Keywords real estate valuation ANN comparative approach machine learning hybrid models
Download PDF Download RIS Download Bibtex

Abstract

The homogenous properties – as flats are – have the set of key features that characterizes them. The area of a flat, the number of rooms and storey number where it is located, the technical state of a building, and the state of the vicinity of the blocks of flats assessed. The database comprises 222 flats with their transaction prices on the secondary estate market. The analysed flats are located in a certain quarter of Wrocław city in Poland. The database is large enough to apply machine learning for successful price predictions. Their close locations significantly lower the influence of clients’ assessments of the attractiveness of the location on the flat’s price. The hybrid approach is applied, where classifying precedes the solution of the regression problem. Dependently on the class of flats, the mean absolute percentage error achieved through the calculations presented in the article varies from 4,4 % to 7,8 %. In the classes of flats where the number of cases doesn’t allow for machine predicting, multivariate linear regression is applied. The reliable use of machine learning tools has proved that the automated valuation of homogenous types of properties can produce price predictions with the error low enough for real applications.
Go to article

Authors and Affiliations

Hubert Anysz
1
ORCID: ORCID
Monika Podwórna
2
Nabi Ibadov
1
ORCID: ORCID
Kunibert Lennerts
3
Kostiantyn Dikarev
4
  1. Warsaw University of Technology, Faculty of Civil Engineering, Al. Armii Ludowej 16, 00-637 Warsaw, Poland
  2. Wrocław University of Science and Technology, Faculty of Civil Engineering , Wyb. Wyspiańskiego 27, 50-370 Wrocław, Poland
  3. Karlsruhe Institute of Technology, Institute of Technology and Management in Construction, Gotthard-Franz-Street 3, 76131 Karlsruhe, Germany
  4. Prydniprovska State Academy of Civil Engineering and Architecture, Department of Construction Technology, 24a, Chernyshevskogo St., Dnipro, 49005, Ukraine

A hybrid model for modelling the salinity of the Tafna River in Algeria

Khemissi Houari Tarik Hartani Boualem Remini Abdelouhab Lefkir Leila Abda Salim Heddam
Journal of Water and Land Development | 2019 | No 40
Keywords Adaptive-Network-Based Fuzzy Inference System (ANFIS), hybrid model, neuro-fuzzy, salinity, salt flow, Tafna River
Download PDF Download RIS Download Bibtex

Authors and Affiliations

Khemissi Houari
Tarik Hartani
Boualem Remini
Abdelouhab Lefkir
Leila Abda
Salim Heddam

Double enveloping worm gear modelling using CAD environment

Piotr Połowniak Mariusz Sobolak Adam Marciniec
Bulletin of the Polish Academy of Sciences Technical Sciences | 2021 | 69 | 2 | e136736 | DOI: 10.24425/bpasts.2021.136736
Keywords globoid surface CAD modelling double enveloping worm gear globoid helix hybrid modelling tooth trace modification
Download PDF Download RIS Download Bibtex

Abstract

This study describes the methodology for modelling a worm and worm wheel of a double enveloping worm gear with the use of a CAD system. An algorithm for generating a globoid helix is described. In addition, the methodology for modelling an hourglass worm thread with a straight axial tooth profile is presented. The shape of the hourglass worm tooth end with and without a trace modification is proposed. Moreover, a method for achieving a geometric modification of the tooth trace was developed. Next, the method for modelling the worm wheel teeth is described. A solid model of using a machining worm as a hob is applied. Owing to the limitations of a CAD system, which prevents the use of a direct machining simulation, an indirect modelling method is introduced. In the present study, different CAD techniques, both solid and surface, are applied. Knowledge of the correct modelling of the hourglass worm and worm wheel facilitates their generation and conducting various analyses, including a tooth contact analysis. CAD models are utilised to analyse the geometrical contact pattern in a CAD environment, to carry out FEM analysis, to manufacture real parts or to prototype models using the technique of rapid prototyping. They can be also used as master models for measurement, e.g. in optical technics.
Go to article

Bibliography

  1.  I. Dudas, The theory and practice of worm gear drives, Penton Press, London, 2000.
  2.  W.P. Crosher, Design and Application of the Worm Gear, ASME Press, New York, 2002.
  3.  F.L. Litvin, Development of Gear Technology and Theory of Gearing, NASA, Levis Research Center, 1999.
  4.  F.L. Litvin and A. Fuentes, Gear Geometry and Applied Theory, Cambridge University Press, 2004.
  5.  L. Dudás, “New technology for manufacturing quasi-globoid worm gearings”, Mater. Sci. Eng. 448, 012035 (2018).
  6.  Y. Chen, Y. Chen, W. Luo, and G. Zhang, “Development and Classification of Worm Drive”, The 14th IFToMMWorld Congress in Taiwan, 2015.
  7.  V. Simon, “Double Enveloping Worm Gear Drive with Smooth Gear Tooth Surface”, in Proc. Int. Conf. on Gearing, Zhengzhou, China, 1988, pp. 191‒194.
  8.  V. Simon, “A New Type of Ground Double Enveloping Worm Gear Drive”, in Proc. ASME 5th Int. Power Transm. and Gearing Conf., Chicago, 1989, pp.281‒288.
  9.  V. Simon, “Load Distribution in Double Enveloping Worm Gears”, J. Mech. Des. 115, 496‒501 (1993).
  10.  V. Simon, “Characteristics of a Modified Double Enveloping Worm Gear Drive”, in Proc. 6th Int. Power Transm. and Gearing Conf., Scottsdale, 1992, pp. 73‒79.
  11.  Y. Zhao and Y. Zhang, “Novel methods for curvature analysis and their application to TA worm”, Mech. Mach. Theory. 97, 155‒170 (2016).
  12.  Y. Zhao and Y. Zhang, “Computing method for induced curvature parameters based on normal vector of instantaneous contact line and its application to Hindley worm pair”. Adv. Mech. Eng. 9, 168781401772188 (2017).
  13.  Y. Zhao, “Meshing analysis for TA worm”, Mech. Mach. Sci. 43, 13–20, (2016)
  14.  Ch. Huai and Y. Zhao, “Variable height modification of TA worm drive”, in Proc. Inst. Mech. Eng. Part C: J. Mech. Eng. Sci. 233, 095440621875726 (2018).
  15.  Y. Zhao, “Edge Tooth Addendum Thickness of Hindley Worm”, Mech. Mach. Sci. 46, 117–124 (2016).
  16.  Y. Zhao, Ch. Huai, and Y. Zhang, “Compound Modification of Globoidal Worm Drive with Variable Parameters”, Appl. Math. Model. 50, 17–38 (2017).
  17.  P. Polowniak and M. Sobolak, “Mathematical description of tooth flank surface of globoidal worm gear with straight axial tooth profile”, Open Eng. 7, 407–415 (2017).
  18.  Q. Wen, H. Xu, and W. Tang, “The Research and Analysis of the New Modification Theory of Toroidal Worm-Gearing”, Int. Conf. Syst. Sci., Eng. Des. Manuf. Informatiz. (ICSEM) 11, 59–62 (2010).
  19.  Y. Chen, W. Luo, Y. Chen, and G. Zhang, “Study on the spur involute gear meshing with planar enveloping hourglass worm based on local conjugate”, Proc. Inst. Mech. Eng. Part C: J. Mech. Eng. Sci. 232, 095440621770821 (2017).
  20.  F. He, Z. Shi, and B. Yu, “Effects of tooth surface modification on planar double-enveloping hourglass worm gear drives”, J. Adv. Mech. Des. Syst. Manuf. 12, JAMDSM0040-JAMDSM0040, (2018).
  21.  W. Xu, D. Qin, and W. Shi, “Direct digital design and simulation of meshing in worm-gear drive”, Chin. J. Mech. Eng. 19, 428–433 (2006).
  22.  L.V. Mohan and M.S. Shunmugam, “Geometrical aspects of double enveloping worm gear drive”, Mech. Mach. Theory. 44, 2053–2065 (2009).
  23.  K.Y. Chen and Ch.B. Tsay, “Mathematical model and worm wheel tooth working surfaces of the ZN-type hourglass worm gear set”, Mech. Mach. Theory. 44, 1701–1712 (2009).
  24.  Ch. Rui, H. Li, J. Yang, W. Wei, “Research on a method for designing land surfaces of a dual-cone double enveloping hourglass worm wheel hob”, J. Adv. Mech. Des. Syst. Manuf. 12, JAMDSM0090-JAMDSM0090 (2018).
  25.  J. Yang, H. Li, Ch. Rui, W. Wei, and X. Dong, “A Method to Generate the Spiral Flutes of an Hourglass Worm Gear Hob”, J. Mech. Des. 140, 063301 (2018).
  26.  Ch. Rui, H. Li, J. Yang, W. Wei, and X. Dong, “A design and generating method for grinding relief surfaces of a dual-cone double enveloping hourglass worm gear hob”, J. Mech. Des. 140, 123301‒1 (2018).
  27.  Z. Lei, Q. Bi, Y. Wang, and H. Ding, “Five-Axis Flank Milling Method of Plane Double Enveloping Hourglass Worm”, Adv. Mat. Res. 314–316, 1523–1532 (2011).
  28.  S. Lagutin, E. Gudov, and B. Fedotov, “Manufacturing and load rating of modified globoid gears”, Balkan J. Mech. Transm. (BJMT). 1, 45–53 (2011).
  29.  Sutyagin, L. Mal’ko, and I. Trifanov, “More efficient machining of globoid worm gears”, Rus. Eng. Res. 35, 623–627 (2015).
  30.  L. Dong, J. Wang, P. Liu, W. Wei, and H. Li, “An NC rough turning method of an enveloping toroidal worm”, Prod. Eng. 6, 129–135 (2012).
  31.  Y. Sun, H. Zheng, Q. Bi, and S. Wang, “Method of accurate grinding for single enveloping TI worm”, Sci. China-technol. Sci. 48, 430–440 (2005).
  32.  Z. Liu, H. Lu, G. Yu, and S. Wang, “A novel CNC machining method for enveloping surface”, Int. J. Adv. Manuf. Technol. 85, 779–790 (2015).
  33.  Z. Liu, H. Lu, S. Wang, and G. Yu, “Digitization modelling and CNC machining for cone-generated double-enveloping worm drive”, Int. J. Adv. Manuf. Technol. 95, 3393–3412 (2018).
  34.  H. Lu, Z. Liu, and S. Wang, “Digitization modelling and CNC machining for enveloping surface parts”, Int. J. Adv. Manuf. Technol. 73, 209–227 (2014).
  35.  A.L. Kheyfets, “Geometrically Accurate Computer 3D Models of Gear Drives and Hob Cutters”, Procedia Eng. 150, 1098–1106 (2016).
  36.  A.L. Kheyfets, “Programming While Construction of Engineering 3D Models of Complex Geometry”, Mat. Sci. Eng. 262, 012111 (2017).
  37.  M. Sobolak, Analysis and synthesis of mating gear tooth surface by discrete methods, Rzeszow University of Technol. Publ., Rzeszow, 2006, [in Polish].
  38.  A.J. Muminovic, M. Colic, E. Mesic, and I. Saric, “Innovative design of spur gear tooth with infill structure”, Bull. Pol. Acad. Sci. Tech. Sci. 68(3), 477–483 (2020).
  39.  W. Ostapski and I. Mukha, “Stress state analysis of harmonic drive elements by FEM”, Bull. Pol. Acad. Sci. Tech. Sci. 55(1), 115–123 (2007).
  40.  M. Batsch, “Mathematical model and tooth contact analysis of convexo-concave helical bevel Novikov gear mesh”, Mech. Mach. Theory 149, 103842 (2020).
  41.  M. Batsch, T. Markowski, S. Legutko, and G.M. Krolczyk, “Measurement and mathematical model of convexo-concave Novikov gear mesh”, Measurement 125, 516–525 (2018).
  42.  M. Sobolak, P. Połowniak, M. Cieplak, M. Oleksy, and K. Bulanda, „Application of polymeric materials for obtaining gears with involute and sinusoidal profile”, Polimery 7‒8, 563‒567 (2020).
  43.  AGMA 6135–A02, Design, Rating and Application of Industrial Globoidal Wormgearing (Metric Edition), Am. Natl. Stand., 2002.
  44.  GOST 16502‒83, Basic requirements for interchange ability. Globoid gears. Tolerances, 1983.
  45.  GOST 17696‒89, Globoid gears. Calculation of geometry, 1989.
  46.  GOST 24438‒80, Globoid gears. Basic worm and basic generating worm, 1980.
  47.  GOST 9369‒77, Globoid gear pairs. Basic parameters, 1977.
  48.  M. Sobolak, P. Polowniak, P.E. Jagielowicz, “Generating of globoid helix in CATIA environment using laws”, Mechanik 7, 632–633 (2016), [in Polish].
Go to article

Authors and Affiliations

Piotr Połowniak
1
ORCID: ORCID
Mariusz Sobolak
1
ORCID: ORCID
Adam Marciniec
1
ORCID: ORCID
  1. Rzeszow University of Technology, The Faculty of Mechanical Engineering and Aeronautics, al. Powstańców Warszawy 12, 35-959 Rzeszow, Poland

A journey from mechanistic to data-driven models in process engineering: dimensionality reduction, surrogate and hybrid approaches, and digital twins

Katarzyna Bizon
Chemical and Process Engineering: New Frontiers | 2023 | vol. 44 | No 3 (24th Polish Conference of Chemical and Process Engineering, 13-16 June 2023, Szczecin, Poland. Guest editor: Prof. Rafał Rakoczy and 8th European Process Intensification Conference, 31.05–2.06.2023, Warsaw, Poland.) | e24 | DOI: 10.24425/cpe.2023.146726
Keywords reduced-order model data-driven model surrogate model hybrid model digital twin
Download PDF Download RIS Download Bibtex

Abstract

The study examines various approaches oriented towards conceptual and numerical reduction of first-principle models, data-driven methodologies for surrogate (black box) and hybrid (grey box) modeling, and addresses the prospect of using digital twins in chemical and process engineering. In the case of numerical reduction of mechanistic models, special attention is paid to methodologies in which simulation data are used to construct light but robust numerical models while preserving all the physics of the problem, yielding reduced-order datadriven but still white-box models. In addition to reviewing various methodologies and identifying their applications in chemical engineering, including industrial process engineering, as well as fundamental research, the study outlines associated problems and challenges, as well as the risks posed by the era of big data.
Go to article

Authors and Affiliations

Katarzyna Bizon
1
ORCID: ORCID
  1. Cracow University of Technology, Faculty of Chemical Engineering and Technology,Warszawska 24, 31-155 Kraków, Poland

Enhancing the performance of deep learning technique by combining with gradient boosting in rainfall-runoff simulation

Barno S. Abdullaeva
Journal of Water and Land Development | 2023 | No 59 | 216-223 | DOI: 10.24425/jwld.2023.148446
Keywords deep learning gradient boosting hybrid model multistep-ahead forecasting rainfall-runoff simulation
Download PDF Download RIS Download Bibtex

Abstract

Artificial neural networks are widely employed as data mining methods by researchers across various fields, including rainfall-runoff (R-R) statistical modelling. To enhance the performance of these networks, deep learning (DL) neural networks have been developed to improve modelling accuracy. The present study aims to improve the effectiveness of DL networks in enhancing the performance of artificial neural networks via merging with the gradient boosting (GB) technique for daily runoff data forecasting in the river Amu Darya, Uzbekistan. The obtained results showed that the new hybrid proposed model performed exceptionally well, achieving a 16.67% improvement in determination coefficient ( R2) and a 23.18% reduction in root mean square error ( RMSE) during the training phase compared to the single DL model. Moreover, during the verification phase, the hybrid model displayed remarkable performance, demonstrating a 66.67% increase in R 2 and a 50% reduction in RMSE. Furthermore, the hybrid model outperformed the single GB model by a significant margin. During the training phase, the new model showed an 18.18% increase in R 2 and a 25% reduction in RMSE. In the verification phase, it improved by an impressive 75% in R 2 and a 33.33% reduction in RMSE compared to the single GB model. These findings highlight the potential of the hybrid DL-GB model in improving daily runoff data forecasting in the challenging hydrological context of the Amu Darya River basin in Uzbekistan.
Go to article

Authors and Affiliations

Barno S. Abdullaeva
1
ORCID: ORCID
  1. Tashkent State Pedagogical University, Faculty of Math and Physics, 27 Bunyodkor Ave, 100070, Tashkent, Uzbekistan

This page uses 'cookies'. Learn more