APPLICATION OF BIG DATA ANALYSIS BASED ON IMPROVED APRIORI ALGORITHM AND ARTIFICIAL INTELLIGENCE IN IMPROVING THE STABILITY OF CNC MACHINE TOOLS
Main Article Content
Abstract
To compensate the machining accuracy of the CNC machine tool is influenced by machine tool parts, the external environment and other factors. Therefore, it is necessary to add appropriate compensation parameters to ensure the stability of machining accuracy. In addition, the compensation parameters of different lathes change at different times in real time. Therefore, an improved Apriori algorithm and an intelligent error compensation model which based on artificial intelligence proposed to establish an intelligent and accurate real- time parameter compensation scheme for the running lathe. The factors that affect the machining accuracy, such as the condition of components and the external environment, form several eigenvalues. Each eigenvalue corresponds to several compensation parameters. A data set consists of several eigenvalues, compensation parameters and a precision value. Several data form a data set. The result of the simulation tests show that the stability of the lathe is improved by 0.695 and 0.713 for the data of the training set and the test set, respectively. The measurement results show that 30 products are carved with the above method, and the accuracy meets the requirements. Therefore, the intelligent error compensation model can improve the stability of turning processing and product qualification rate.
Downloads
Article Details
Section
How to Cite
References
[1] J. He, Z.L. Guo, S.B. Luo, et al., Ultra-precision machiningtechnology of off-axis paraboloid surface based on PMAC time-based control, Optics and Precision Engineering, 29(8), 2021,7–8.
[2] D. Lv, J.H. Zhang, D.W. Wang, et al., Technical statusand countermeasures of dynamic accuracy of domestic CNCmachine tools, Aeronautical Manufacturing Technology, 65(6),2022, 22–33.
[3] H. Zhao, X. Zhou, and S.T. Zhang, Local optimization of five-axis machining tool orientation based on angular accelerationof machine tool, Machine Tool & Hydraulics, 50(11), 2022,94–97.
[4] X. Feng, H. Mao, Z. Xin, et al., Study on engineeringapplication of servo control system in giant friction weldingmachines, Mechatronic Systems and Control, (3), 2023,122–132.
[5] K. Liu, W. Han, Y.Q. Wang, H. Liu, and L. Song,Review on thermal error compensation for feed axes of CNCmachine tools, Journal of Mechanical Engineering, 57(3), 2021,156–173.
[6] K. Bai, Z. Li, and L.H. Wu, Triggered probe error speedcompensation in on-machine measurement of machine tool,Modular Machine Tool & Automatic Manufacturing Technique,2(22), 2021, 91–98.
[7] Z. Zhao, Z.F. Lou, Z.N. Zhang, et al., Geometric error modelof CNC machine tools based on Abbe principle, Optics andPrecision Engineering, 28(4), 2020, 885–897.
[8] F. Tan, C.N. Li, H. Xiao, Z.Q. Su, and K.A. Zhen, A thermalerror prediction method for CNC machine tool based onLSTM recurrent neural network, Chinese Journal of ScientificInstrument, 41(9), 2020, 79–87.
[9] H.R. Patel, Fuzzy-based metaheuristic algorithm for optimiza-tion of fuzzy controller: fault-tolerant control application, Inter-national Journal of Intelligent Computing and Cybernetics,15(4), 2022, 599–624.
[10] H.R. Patel and V.A. Shah, Type-2 fuzzy logic applicationsdesigned for active parameter adaptation in metaheuristicalgorithm for fuzzy fault-tolerant controller, InternationalJournal of Intelligent Computing and Cybernetics, 16(2), 2023,198–222.
[11] A. Kumar, Reinforcement learning: Application and advancestowards stable control strategies, Mechatronic Systems andControl, (1), 2023, 53–57.
[12] A. Kukker and R. Sharma, Stochastic genetic algorithm-assisted fuzzy q-learning for robotic manipulators, ArabianJournal for Science and Engineering, 46, 2021, 9527–9539.
[13] A.K. Yadav, V. Kumar, A.S, Pandey, et al., Wind farmintegrated fuzzy logic-based facts controlled power systemstability analysis, Mechatronic Systems and Control, (4), 2023,172–181.
[14] K. Amit and S. Rajneesh, Neural reinforcement learningclassifier for elbow, finger and hand movements, Journal ofIntelligent and Fuzzy Systems, 35, 2018, 1–11.
[15] R.L. Kumar, F. Khan, S. Din, et al., Recurrent neural networkand reinforcement learning model for COVID-19 prediction,Frontiers in Public Health, 9, 2021, 744100.
[16] N.A. Vishnu, M.L.G. Rubell, and P. Gopakumar, Rein-forcement learning based energy management system forhybrid electric vehicles, Proc. 2023 3rd International Conf.on Advances in Computing, Communication, Embeddedand Secure Systems (ACCESS), Kalady, 2024-03-16, DOI:10.1109/ACCESS57397.2023.10200701.
[17] K.N. Fang and B.C. Xie, Research on dealing with missing databased on clustering and association rule, Statistical Research,28(2), 2011, 87–92.
[18] M.W. Tian, L. Zhang, P. Guo, H. Zhang, Q. Chen, Y. Lei,and A. Xue, Data dependence analysis for defects data of relayprotection devices based on Apriori algorithm, IEEE Access,8, 2020, 120647–120653.
[19] B.A. Khuwaileh, M. Al-Shabi, and M. Assad, Artificial neuralnetwork based particle swarm optimization solution approachfor the inverse depletion of used nuclear fuel, Annals of NuclearEnergy, 4(22), 2021, 108–116.
[20] Z. Shi, W. Zheng, and W. Yin, Improving the reliability ofthe prediction of terrestrial water storage in Yunnan using theartificial neural network selective joint prediction model, IEEEAccess, 1(12), 2021, 305–311.