Prediction and Simulation of Machining Parameters in Ultrasonic Assisted EDM Process Using Hybrid ANFIS-PSO Method
محورهای موضوعی : Manufacturing process monitoring and control
Mohamad Reza Shabgard
1
,
Gohar Ranjbari
2
1 - Department of Manufacturing Engineering, University of Tabriz, Tabriz, Iran
2 - Department of Mechanical Engineering, Ara.C., Islamic Azad University, Jolfa, Iran
کلید واژه: ANFIS, ANFIS-PSO, US/EDM, MRR, Ra, TWR,
چکیده مقاله :
In this study, the prediction capabilities of the adaptive neuro-fuzzy inference system (ANFIS) and the particle swarm optimization (PSO)-based ANFIS were compared. First, the material removal rate (MRR), surface roughness (Ra), and tool wear ratio (TWR) were modeled using the ANFIS technique during the ultrasonic-assisted electrical discharge machining (US/EDM) process. The ANFIS model was developed to predict these output parameters, and subsequently, its parameters were optimized using PSO to reduce prediction error. The pulse-on time (Ton) and current (I) were selected as input factors. The models were trained, tested, and validated with experimental data, and statistical analyses were conducted to evaluate the effectiveness of both ANFIS and ANFIS–PSO approaches. The greatest reduction in the average prediction error percentage was observed for MRR, decreasing from 10.87% in the ANFIS model to 6.19% in the ANFIS–PSO model. Overall, the experimental results demonstrated that the ANFIS–PSO algorithm provided superior performance in estimating machining parameters compared with the conventional ANFIS model.
In this study, the prediction capabilities of the adaptive neuro-fuzzy inference system (ANFIS) and the particle swarm optimization (PSO)-based ANFIS were compared. First, the material removal rate (MRR), surface roughness (Ra), and tool wear ratio (TWR) were modeled using the ANFIS technique during the ultrasonic-assisted electrical discharge machining (US/EDM) process. The ANFIS model was developed to predict these output parameters, and subsequently, its parameters were optimized using PSO to reduce prediction error. The pulse-on time (Ton) and current (I) were selected as input factors. The models were trained, tested, and validated with experimental data, and statistical analyses were conducted to evaluate the effectiveness of both ANFIS and ANFIS–PSO approaches. The greatest reduction in the average prediction error percentage was observed for MRR, decreasing from 10.87% in the ANFIS model to 6.19% in the ANFIS–PSO model. Overall, the experimental results demonstrated that the ANFIS–PSO algorithm provided superior performance in estimating machining parameters compared with the conventional ANFIS model.
[1] Zhang, X., Zhou, J., Liu, C., Li, K., Shen, W., Lin, Z., ... and Lin, N. 2019. Effects of Ni addition on mechanical properties and corrosion behaviors of coarse-grained WC-10 (Co, Ni) cemented carbides. International Journal of Refractory Metals and Hard Materials. 80:123-129. doi:10.1016/j.ijrmhm.2019.01.004.
[2] Masuzawa T., Tsukamoto J. and Fujino M. 1989. Drilling of deep micro holes by EDM. CIRP Ann 38:195–198.
[3] Ye SL., Su J., Jia, Z.X. and Hua R.2004. Study on the mechanism of high speed small hole drilling by EDM. Mater Sci Forum. 471:302–306. doi:10.4028/www.scientific.net/MSF.471-472.302.
[4] Mohan B., Rajadurai A. and Satyanarayana, K.G. 2002. Effect of SiC and rotation of electrode on electric discharge machining of Al–SiC composite. J Mater Process Technol. 124(3):297–304. doi:10.1016/S0924-0136(02)00202-9.
[5] Wong Y.S., Lim, L.C. and Lee LC. 1995. Effects of flushing on electro-discharge machined surfaces. J Mater Process Technol. 48(1):299–305. doi:10.1016/0924-0136(94)01662-K.
[6] Zhang QH., Du R., Zhang, J.H. and Zhang QB .2006. An investigation of ultrasonic assisted electrical discharge machining in gas. International J Mach Tool Manuf. 46(12):1582–1588. doi:10.1016/j.ijmachtools.2005.09.023.
[7] Chen, B., Tao, M. and Luo, Z. 2024. Effect of ultrasonic assisted EDM based on horizontal vibration on deep and small hole machining. Scientific Reports. 14(1):28146.
[8] Pravin, T., Subramanian, M. and Ranjith, R. 2022. Clarifying the phenomenon of ultrasonic assisted electric discharge machining. Journal of the Indian Chemical Society. 99(10):100705. doi:10.1016/j.jics.2022.100705.
[9] Singh, P., Yadava, V. and Narayan, A. 2024. Machining performance characteristics of Ti–6Al–4V alloy due to ultrasonic assisted micro-EDM using rotating tool electrode. Journal of The Institution of Engineers (India): Series D. 105(1):155-171.doi:10.1007/s40033-023-00460-3.
[10] Ao, S., Gong, H., Ni, H., Gui, S., Feng, C. and Wang, Y. 2024. Design of ultrasonic-assisted EDM system for drilling small holes based on local resonance principle. The International Journal of Advanced Manufacturing Technology. 134(9):4821-4838.doi:10.1007/s00170-024-14426-6.
[11] Naresh, C., Bose, P. S. C. and Rao, C. S. P. 2020. ANFIS based predictive model for wire edm responses involving material removal rate and surface roughness of Nitinol alloy. Materials Today: Proceedings. 33:93-101. doi:10.1016/j.matpr.2020.03.216.
[12] Thejasree, P., Manikandan, N., Sunheriya, N., Giri, J., Sathish, T., Chadge, R. and Parthiban, A. 2024. Application of ANFIS approach for prediction of performance measures in wire electric discharge machining of SAE 1010. Interactions. 245(1):193.doi:10.1007/s10751-024-02030-9.
[13] Kumar, L., Goyal, A. and Pathak, V. K. 2025. Prediction and optimization of WEDM parameters for machining of NiTi-shape memory alloy using ANFIS-PSO approach. Discover Applied Sciences. 7(4):249.doi:10.1007/s42452-025-06663-5.
[14] Goyal, A., Sharma, D., Bhowmick, A. and Pathak, V. K. 2022. Multi-objective optimization and characterization of cylindricity and material removal rate in nanographene mixed dielectric EDM using ANFIS and MOSOA. Sādhanā. 47(3):139. doi:10.1007/s12046-022-01914-2.
[15] Hasan, M. M., Saleh, T. and Sophian, A. 2025. ANN-based ensemble model for predicting micro-EDM responses and machining variability. Machining Science and Technology. 29(2):259-293. doi:10.1080/10910344.2025.2475467.
[16] Pourasl, H. H., Javidani, M., Khojastehnezhad, V. M. and Vatankhah Barenji, R. 2022. The performance prediction of electrical discharge machining of AISI D6 tool steel using ANN and ANFIS techniques: a comparative study. Crystals. 12(3):343. doi:10.3390/cryst12030343.
[17] Saffaran, A., Azadi Moghaddam, M. and Kolahan, F. 2020. Optimization of backpropagation neural network-based models in EDM process using particle swarm optimization and simulated annealing algorithms. Journal of the Brazilian Society of Mechanical Sciences and Engineering. 42(1):73. doi:10.1007/s40430-019-2149-1.
[18] Xu, L., Huang, C., Li, C., Wang, J., Liu, H. and Wang, X. 2021. Estimation of tool wear and optimization of cutting parameters based on novel ANFIS-PSO method toward intelligent machining. Journal of Intelligent Manufacturing, 32(1):77-90.doi:10.1007/s10845-020-01559-0.
[19] Singh, N. K., Upadhyay, R. K., Singh, Y. and Sharma, A. 2020. Intelligent hybrid approaches for ensuring better prediction of gas-assisted EDM responses. SN Applied Sciences, 2(5):914. doi:10.1007/s42452-020-2654-y.
[20] Marini, F. and Walczak, B. 2015. Particle swarm optimization (PSO). A tutorial. Chemometrics and intelligent laboratory systems. 149:153-165. doi:10.1016/j.chemolab.2015.08.020.
