Prediction of Time-series Friction Data using ANFIS

Yıl 2025, Cilt: 39 Sayı: 1, 121 - 134

Cem Korkmaz , İlyas Kacar

Öz

Modelleme bilim ve endüstride sıklıkla kullanılmaktadır. Sürtünme, aşınma ve korozyon sorunları yer fıstığı sınıflandırma makinelerinde ana tasarım kriterleridir. Bu çalışmada, sürtünme kuvveti verilerinin zaman serisi uyarlanabilir nöro-bulanık çıkarım sistemi (ANFIS) ile modellenmiştir. Makine öğrenimi, açık programlama olmadan tahmin ve sınıflandırma için modeller geliştirmeye odaklanır. Sürtünme kuvveti verileri, ayrık eleman yöntemine (DEM) dayalı bir simülasyondan elde edilmiştir. Simülasyon, 60 saniyelik gerçek zamanı hesaplamak için 63 gün, 18 saat ve 27 dakika sürmektedir. Takagi-Sugeno tipi bir ANFIS ağı oluşturulmuştur. Ağ, ızgara bölümleme yöntemi kullanılarak kümelenmiştir. ANFIS, sürtünme verilerini modelleyerek makine performansını optimize etmeye yardımcı olur. Elde edilen yer fıstığı çekirdek sınıflandırma modelinde korelasyon değeri 0,798854 ve ortalama karesel hatanın kökü 0,51417 N'dir. Ortalama mutlak hatanın yüzdesi %1,6658 olarak bulunmuştur. 100 iterasyon çalıştırılmıştır. Hesaplamalar 20,70228 saniye sürmektedir. Model yüksek doğrusal ilişkiye sahiptir. ANFIS ağının verilerin herhangi bir ön işlemden geçirilmesi ihtiyacını ortadan kaldırdığı da gözlemlenmiştir. Çalışmada kullanılan ağın arka planı, hiper-parametreleri ve tahmin performansı sunulmuştur.

Anahtar Kelimeler

İç yer fıstığı sınıflama, Ayrık eleman metodu, Uyarlanabilir nöro-bulanık çıkarım sistemi, Modelleme, Kestirim

Etik Beyan

Veri ve Kod Erişilebilirliği Hiçbir veri veya kod gerekli değildir. Yazar Katkıları Tüm yazarlar eşit katkıda bulunmuştur. Çıkar çatışmaları / Rekabet eden çıkarlar Yazarlar, bu makalenin yayınlanmasıyla bağlantılı olarak beyan edecekleri herhangi bir çıkar çatışması veya rakip çıkarları olmadığını beyan ederler

Destekleyen Kurum

Bu çalışma, kamu, ticari veya kâr amacı gütmeyen sektörlerdeki fon kuruluşlarından herhangi bir özel hibe almamıştır.

Teşekkür

Çukurova Üniversitesi Ziraat Fakültesi'ne, Karadeniz Teknik Üniversitesi'ne ve Dr. Mehmet Seyhan'a ayrık elemanlar yöntemi simülasyonları için Ansys Rocky DEM© ve ML yönteminin kodlanması için Matlab© programlarını eğitim amaçlı kullanma imkanı sağladıkları için teşekkür ederiz. Bu çalışmanın inceleme ve değerlendirme aşamasındaki değerli katkılarından dolayı editörlere, hakemlere ve katkıda bulunanlara içtenlikle teşekkür ederiz.

Prediction of Time-series Friction Data using ANFIS

Öz

Modelling is frequently used in science and industry. Friction, wear, and corrosion issues are the main design criteria in peanut kernel grading machines. In this study, the time-series of friction force data is modelled with adaptive neuro-fuzzy inference system (ANFIS). Machine learning focuses on developing models for prediction and classification without explicit programming. The data on the friction force is obtained from a simulation based on the discrete element method. The simulation takes 63 days, 18 hours and 27 minutes to calculate the real time of 60 seconds. A Takagi-Sugeno type ANFIS network is constructed. The network is clustered using grid partitioning method. ANFIS helps to optimise machine performance by modelling friction data. In the obtained peanut kernel classification model, the correlation value is 0.799 and the root of the mean square error is 0.514 N. The percentage of the mean absolute error is found to be 1.666%. 100 iterations are run. Calculations take 20.7 seconds. The model has a high linear relationship. It is also observed that the ANFIS network eliminates the need for any pre-processing of the data. Background of the network used, its hyper-parameters, and the prediction performance are presented in the study.

Anahtar Kelimeler

Peanut kernel classification, Discrete element method, Adaptive neuro-fuzzy inference system, Modelling, Prediction

Etik Beyan

Data and Code Availability No data or code is necessary. Author Contributions All authors have contributed equally. Conflicts of interest/Competing interests The authors declare that they have no conflicts of interest or competing interests to declare in connection with the publication of this article

Destekleyen Kurum

This study has not received any specific grants from funding organisations in the public, commercial or non-profit sectors.

Teşekkür

We would like to thank Çukurova University Faculty of Agriculture, Karadeniz Technical University, and Dr. Mehmet Seyhan for providing the opportunity to use Ansys Rocky DEM© for discrete element method simulations and Matlab© for coding the ML method for educational purposes, respectively. We would like to sincerely thank the editors, referees, and contributors for their valuable contributions during the review and evaluation phase of this study.

Kaynakça

• Adhav P, Besseron X, Estupinan AA, Peters B (2024). Development and validation of CFD-DEM coupling interface for heat & mass transfer using partitioned coupling approach. International Communications in Heat and Mass Transfer, 157: 107801.
• Akcali İD, Mutlu H, Ercan U (2014). Mathematical Model of a Sorting Machine. Journal of Agricultural Machinery Science, 10(3): 229-234.
• Asylbekov E, Poggemann L, Dittler A, Nirschl H (2024). Discrete Element Method Simulation of Particulate Material Fracture Behavior on a Stretchable Single Filter Fiber with Additional Gas Flow. Powders, 3(3): 367-391.
• Brockwell PJ, Davis RA (2002). Introduction to time-series and forecasting: Springer. New York , USA, p.449 Bui VH, Bui MD, Rutschmann P (2019). Combination of discrete element method and artificial neural network for predicting porosity of gravel-bed river. Water, 11(7): 1461.
• Caruana R, Lou Y, Gehrke J, Koch P, Sturm M, Elhadad N (2015). Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. Paper presented at the Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining.
• Chen W, Shi K (2021). Multi-scale attention convolutional neural network for time-series classification. Neural Networks, 136: 126-140.
• Chou K-Y, Yeh Y-W, Chen Y-T, Cheng Y-M, Chen Y-P (2020). Adaptive neuro fuzzy inference system based MPPT algorithm applied to photovoltaic systems under partial shading conditions. Paper presented at the 2020 International Automatic Control Conference (CACS).
• Cui X, Li X, Du Y, Bao Z, Zhang X, Hao J, Hu Y (2024). Macro-micro numerical analysis of granular materials considering principal stress rotation based on DEM simulation of dynamic hollow cylinder test. Construction and Building Materials, 412: 134818.
• Cunha N, da Silva LHM, da Cruz Rodrigues AM (2024). Drying of Curcuma longa L. slices by refractance window: Effect of temperature on thermodynamic properties and mass transfer parameters. Heat and Mass Transfer, 60(4): 617-626.
• Ge M, Zheng G (2024). Fluid–Solid Mixing Transfer Mechanism and Flow Patterns of the Double-Layered Impeller Stirring Tank by the CFD-DEM Method. Energies, 17(7): 1513.
• Hu G, Zhou B, Zheng W, Li C, Wang H (2024). A ML-based drag model for sand particles in transition flow aided by spherical harmonic analysis and resolved CFD-DEM. Acta Geotechnica, 20(1):461-474.
• Irshaid M, Abu-Eisheh S (2023). Application of adaptive neuro-fuzzy inference system in modelling home-based trip generation. Ain Shams Engineering Journal, 14(11): 102523.
• Jang J-S, Sun C-T (1995). Neuro-fuzzy modeling and control. Proceedings of the IEEE, 83(3): 378-406.
• Kacar İ (2023). Scientific Principles of Mechanical Design and Analysis (Vol. 381): Academician bookshop.
• Khalaf AH, Lin B, Abdalla AN, Han Z, Xiao Y, Tang J (2024). Enhanced prediction of corrosion rates of pipeline steels using simulated annealing-optimized ANFIS models. Results in Engineering, 24: 102853.
• Kibriya G, Orosz Á, Botzheim J, Bagi K (2023). Calibration of micromechanical parameters for the discrete element simulation of a masonry arch using artificial intelligence. Infrastructures, 8(4): 64.
• Korkmaz C (2023). The place of oganic and organomineral fertilizer production in sustainable agriculture. In A Bayat (Ed.), Sustainable Agriculture Technologies-II), Ankara: İKSAD. Vol. 244, pp. 183-205
• Korkmaz C, Kacar İ (2024). Explaining data preprocessing methods for modeling and forecasting with the example of product drying. Journal of Tekirdag Agricultural Faculty, 21(2): 482-500.
• LeCun Y, Bengio Y, Hinton G (2015). Deep learning. Nature, 521(7553): 436-444.
• Lipton ZC (2015). A Critical Review of Recurrent Neural Networks for Sequence Learning. arXiv Preprint, CoRR, abs/1506.00019.
• Mahboob A, Hassanshahi O, Tabrizi AS (2023). Three-dimensional simulation of granular materials by discrete element method (DEM) by considering the fracture effect of particles. Journal of Civil Engineering Researchers, 5(2): 14-28.
• Murphy KP (2022). Probabilistic ML: an introduction: MIT press, London, England, p:864.
• Pan SJ, Yang Q (2009). A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10): 1345-1359.
• Qiao J, Hu K, Yang J, Wang Y, Liu J, Zhou E, . . . Duan C (2024). Research on enhancement of screening performance of a novel drum screen based on the Discrete Element Method simulation. Powder Technology, 437: 119567.
• Ramirez CE, Sermet Y, Demir I (2024). HydroCompute: An open-source web-based computational library for hydrology and environmental sciences. Environmental Modelling & Software, 175: 106005.
• Reineking L, Fischer J, Mjalled A, Illana E, Wirtz S, Scherer V, Mönnigmann M (2024). Convective drying of wood chips: Accelerating coupled DEM-CFD simulations with parametrized reduced single particle models. Particuology, 84: 158-167.
• Rocky DEM© Ansys (2021). DEM technical manual 4.4. 3.
• Siegmann E, Enzinger S, Toson P, Doshi P, Khinast J, Jajcevic D (2021). Massively speeding up DEM simulations of continuous processes using a DEM extrapolation. Powder Technology, 390: 442-455.
• Ström H, Luo H, Xiong Q (2024). Perspectives on Particle–Fluid Coupling at Varying Resolution in CFD-DEM Simulations of Thermochemical Biomass Conversion. Energy & Fuels, 38(18): 17179-17190.
• Sutton RS (2018). Reinforcement learning: An introduction. A Bradford Book. The MIT Press, London, England, p. 548.
• Tien Bui D, Khosravi K, Li S, Shahabi H, Panahi M, Singh VP, . . . Chen W (2018). New hybrids of anfis with several optimization algorithms for flood susceptibility modeling. Water, 10(9): 1210.
• Ugurluay S, Akcali ID (2021). Development of a vibrationless sorting system. Spanish journal of agricultural research, 19(1): 204.
• Wu W, Chen K, Tsotsas E (2024). Prediction of rod-like particle mixing in rotary drums by three ML methods based on DEM simulation data. Powder Technology, 448: 120307.
• Xie Z, Gu X, Shen Y (2022). A ML study of predicting mixing and segregation behaviors in a bidisperse solid–liquid fluidized bed. Industrial & Engineering Chemistry Research, 61(24): 8551-8565.
• Yao L, Xiao Z, Liu J, Zhang Q, Wang M (2020). An optimized CFD-DEM method for fluid-particle coupling dynamics analysis. International Journal of Mechanical Sciences, 174: 105503.
• Zhang C, Chen Y, Wang Y, Bai Q (2024). Discrete element method simulation of granular materials considering particle breakage in geotechnical and mining engineering: A short review. Green and Smart Mining Engineering, 1(2): 190-207.
• Zhang T, Li S, Yang H, Zhang F (2024). Prediction of constrained modulus for granular soil using 3D discrete element method and convolutional neural networks. Journal of Rock Mechanics and Geotechnical Engineering, 16(11): 4769-4781.
• Zhang Y, Cao Z, Liu C, Huang H (2024). Fluid-solid coupling numerical simulation of micro-disturbance grouting treatment for excessive deformation of shield tunnel. Underground Space, 19:87-100.
• Zhao Z, Zhou L, Bai L, Wang B, Agarwal R (2024). Recent advances and perspectives of CFD–DEM simulation in fluidized bed. Archives of Computational Methods in Engineering, 31(2): 871-918.
• Zhou L, Wang B, Cao Y, Zhao Z, Agarwal R (2024). Fluidisation of spherocylindrical particles: computational fluid dynamics–Discrete element method simulation and experimental investigation. Engineering Applications of Computational Fluid Mechanics, 18(1): 2297537.