Endüstriyel Sıvı Seviye Denetim Sisteminin Yapay Sinir Ağları ile Modellenmesi

Abstract

Sistem modelleme, teori ile deneysel çalışmaların birleşmesini sağlayan, araştırma faaliyetlerinde önemli yer tutan bilimsel bir yöntemdir. Sistem modeli ile gerçek test ve deneylerle elde edilecek verilerin, maliyet açısından daha ekonomik ve zamandan tasarrufla sistemin kritik noktalarının temini sağlanmaktadır. Bazı sistem modellerinin sadece analitik denklem ve yöntemlerle elde edilmesi oldukça zordur. Bu noktada, yapay sinir ağları, karmaşık, belirsiz, doğrusal olmayan sistemlerin modellenmesinde alternatif bir yoldur. Yapay sinir ağları, insan beynini örnek alarak, mevcut örneklerden öğrenen, gürültülü, eksik, doğrusal olmayan verilerle sonuç üretebilen, bir kez öğrendikten sonra yüksek hızda ve doğrulukta tahmin ve genelleme yapabilen bir yapay zeka sistemidir. Bu çalışmada, eğitim amaçlı deneysel bir süreç denetim sistemi olan, GUNT Hamburg firmasının üretmiş olduğu RT512 sıvı seviye denetim sisteminin yapay sinir ağı ile modellenmesi gerçekleştirilmiştir. Dinamik modelin oluşturulması için, sistem açık çevrim modunda çalıştırılarak, bir giriş-çıkış veri seti oluşturulmuştur. Bu sette, verilen kontrol işaretine karşılık sıvı seviye tüpünde görülen seviye değişimi dikkate alınmıştır. Bu işlem için, bilgisayar, Arduino, MCP4725 DAC, akım/gerilim, gerilim/akım dönüştürücüler kullanılarak belli sayıda giriş verisine karşılık, belli sayıda çıkış verisi elde edilmiştir. Geliştirilen YSA modelinde regresyon eğrileri ile model çıkışı ile sistemden alınan test verileri arasındaki ilişki görülmüş olup yüksek doğruluk elde edilmiştir.

Keywords

• Sıvı seviye denetimi
• yapay sinir ağları
• sistem modelleme
• GUNT RT 512
• geri yayılım algoritması

Artificial Neural Network Modeling of Industrial Liquid Level Control

Abstract

System modeling is a scientific method that combines theory with experimental studies and has an important place in research activities. With the system model, the data to be obtained through real tests and experiments are provided more economically in terms of cost and the critical points of the system are provided with time savings. Some system models are very difficult to obtain using only analytical equations and methods. At this point, artificial neural networks are an alternative way to model complex, uncertain, nonlinear systems. Artificial neural network is an artificial intelligence system that takes the human brain as an example, learns from existing examples, can produce results with noisy, incomplete, non-linear data, and can make predictions and generalizations with high speed and accuracy after learning once. In this study, RT 512 liquid level control system produced by GUNT Hamburg, an experimental process control system for educational purposes, was modeled with an artificial neural network. In order to create the dynamic model, an input-output data set was created by operating the system in open-loop mode. In this set, the level change seen in the liquid level tube against the given control sign has been taken into account. For this process, a certain number of output data was obtained for a certain number of input data by using computer, Arduino, MCP4725 DAC, current/voltage, voltage/current converters. In the developed ANN model, the relationship between the regression curves and the model output and the test data taken from the system was observed and high accuracy was obtained.

Keywords

• Liquid level control
• artificial neural networks
• system modeling
• GUNT RT 512
• back propagation algorithm

References

1. 1. Yu S., Lu X., Zhou Y., Feng Y., Qu T. and Chen H.: ‘Liquid Level Tracking Control of Three-tank Systems’, International Journal of Control, Automation and Systems, 2020, 18, (10): 2630-2640.
2. 2. Başçi A. and Derdiyok A.: ‘Implementation of an adaptive fuzzy compensator for coupled tank liquid level control system’, Measurement, 2016, 91: 12-18.
3. 3. Jianjun Z.: ‘Design of Fuzzy Control System for Tank Liquid Level Based on WinCC and Matlab’, in Editor (Ed.)^(Eds.): ‘Book Design of Fuzzy Control System for Tank Liquid Level Based on WinCC and Matlab’ (IEEE, edn.),2014: 55-57.
4. 4. Pan H., Wong H., Kapila V., and De Queiroz M.S.: ‘Experimental validation of a nonlinear backstepping liquid level controller for a state coupled two tank system’, Control Engineering Practice, 2005, 13, (1): 27-40.
5. 5. Samin R.E., Jie L.M., and Zawawi M.A.: ‘PID implementation of heating tank in mini automation plant using Programmable Logic Controller (PLC)’, in Editor (Ed.)^(Eds.): ‘Book PID implementation of heating tank in mini automation plant using Programmable Logic Controller (PLC)’ (IEEE, edn.), 2011: 515-519.
6. 6. Derdiyok A.,Basçi A.: ‘The application of chattering-free sliding mode controller in coupled tank liquid-level control system’, Korean J. Chem. Eng., 2013, 30, (3): 540-545.
7. 7. Basheer I.A. and Hajmeer M.: ‘Artificial neural networks: fundamentals, computing, design, and application’, Journal of Microbiological Methods, 2000, 43, (1): 3-31.
8. 8. Marshiana D., Thirusakthimurugan P.: ‘Measurement and Control of Non-Linear Data Using ARMA Based Artificial Neural Network’, International Journal of Nonlinear Sciences and Numerical Simulation, 2018, 19, (5): 499 -510.

9. 9. Simeth A., Plaßmann J.,Plapper P.: ‘Detection of Fluid Level in Bores for Batch Size One Assembly Automation Using Convolutional Neural Network’, Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilient Production Systems, 2021, 632: 86-93.
10. 10. Saggar M,,Mercli T.,Andoni S., Miikkulainen R.: ‘System Identification for the Hodgkin-Huxley Model using Artificial Neural Networks’. Proc. Proceedings of International Joint Conference on Neural Networks,2007: 2239-2244.
11. 11. Noel M.M., Pandian B.J.: ‘Control of a nonlinear liquid level system using a new artificial neural network based reinforcement learning approach’, Applied Soft Computing, 2014, 23,: 444-451
12. 12. Çelik B., Birtane S., Dikbıyık E., Erdal H.: ‘Liquid Level Process Control with Fuzzy Logic Based Embedded System’. Proc. nternational Conference on Electrical and Electronics Engineering, ELECO 2015, 2015:874-878.
13. 13. Bhar, I., and Mandal, N.: ‘An ANN Based Temperature Compensation Technique for Level Measurement Using Float and Hall Sensor’, in Editor (Ed.)^(Eds.): ‘Book An ANN Based Temperature Compensation Technique for Level Measurement Using Float and Hall Sensor’ (IEEE, edn.), 2018 15th IEEE India Council International Conference (INDICON), 2018: 1-5.
14. 14. Lata A., Mandal N..: ‘ANN-based liquid level transmitter using force resistive sensor for minimisation of hysteresis and non-linearity error’, IET Science, Measurement and Technology, 2020,14, (10): 923 -930.
15. 15. Nabiyev, V.: ‘Yapay Zeka’ ,Seçkin Yayıncılık, 6, Ankara (2021)
16. 16. Quarto M., D'Urso G., Giardini C.: ‘Micro-EDM optimization through particle swarm algorithm and artificial neural network’, Precision Engineering, 2022, 73: 63-70.
17. 17. Khamesipoura M., Chitsaz I., Salehib M., Alizadeniab S.: ‘Component sizing of a series hybrid electric vehicle through artificial neural network’, Energy Conversion and Management, 2022, 254: 1-11.
18. 18. Tam V.W.Y., Butera A., Le K.N., Da Silva L.C.F., Evangelista A.C.J.: ‘A prediction model for compressive strength of CO2 concrete using regression analysis and artificial neural networks’, Construction and Building Materials, 2022, 324: 1-13.
19. 19. Cormerais R., Longo R., Duclos A., Wasselynck G., Berthiau G.: ‘Non destructive Eddy Currents inversion using Artificial Neural Networks and data augmentatio’, NDT and E International, 2022, 129: 1-16.
20. 20. Zhang K., Zhang Z., Han Y., Gu Y., Qiu Q., Zhu X.: ‘Artificial neural network modeling for steam ejector design’, Applied Thermal Engineering, 2022, 204: 1-9.
21. 21. Mohammed M., Taher M.K., Khudhair S.: ‘Prediction of turbojet performance by using artificial neural network’, Materials Today: Proceedings, 2021:1513-1522.
22. 22. Moayedi H., Mehrabi M., Mosallanezhad M., Rashid A.S.A. and Pradhan B.: ‘Modification of landslide susceptibility mapping using optimized PSO-ANN technique’, Engineering with Computers, 2019, 35, (3): 967-984.
23. 23. Liu Z., Karimi I.A.: ‘Gas turbine performance prediction via machine learning’, Energy, 2020, 192: 1-10.
24. 24. Öztemel, E.: ‘Yapay Sinir Ağları’ ,Papatya Yayıncılık, 3,İstanbul(2012)
25. 25. Kaastra I., Boyd M.: ‘Designing a neural network for forecasting financial and economic time series’, Neurocomputing, 1996, 10, (3): 215-236.