Improved PI neural network-based tension control for stranded wire helical springs manufacturing

Abstract During the winding process of stranded wire helical springs (SWHSs), uneven wire tension always results in high rejection rate and non-compliance service life of SWHSs. Combining the proportion integral neural network (PINN) with a simplified actuator model, this paper presents a new control scheme for the SWHS CNC machine to keep the wire tension uniform. The PINN is improved by introducing an error variance ratio, accounting for the interaction between wires, as a modifying factor in the second hidden layer. The actuator model is simplified based on the analysis of the dynamic characteristics of the actuator. The output value of the improved PINN is transferred into control voltage value by the simplified model. The tension of each wire is controlled by an improved PINN. In order to enhance the control performance, the network parameters are updated using the gradient-based back-propagation method. The validity and consistency of the improved PINN are verified by experiments. The results indicate that (1) the computation load is slight; (2) the rising time of the step response is within 1 s; (3) 89%-96% of tension deviation values of the wire 1 and wire 3 under different process parameters are within 10% of the reference tension value; (4) the standard deviation of the wire 2 with large disturbance is 8.24 N. Compared with other algorithms (incremental PI, multiple PIDNN, PI based particle swarm optimization), the control scheme based on the improved PINN has less computation load, faster response speed and better performance in the time-varying and nonlinear system with larger disturbance.

[1]  Chul-Goo Kang,et al.  MIMO Tension Modelling and Control for Roll-to-roll Converting Machines , 2008 .

[2]  Hyunkyoo Kang,et al.  Advanced taper tension method for the performance improvement of a roll-to-roll printing production line with a winding process , 2012 .

[3]  Vincent Gassmann,et al.  Fixed-Order $H_{\infty}$ Tension Control in the Unwinding Section of a Web Handling System Using a Pendulum Dancer , 2012, IEEE Transactions on Control Systems Technology.

[4]  Hua Lu,et al.  Development of PLC-based Tension Control System , 2007 .

[5]  Yang Ruqing,et al.  Research on a precision tension control system with a magnetic particle clutch as the actuator , 2005 .

[6]  W. B. Heginbotham.  The future and scope of AMT , 1985 .

[7]  Qiang Liu,et al.  Data-Based Hybrid Tension Estimation and Fault Diagnosis of Cold Rolling Continuous Annealing Processes , 2011, IEEE Transactions on Neural Networks.

[8]  M. Valipour,et al.  Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir , 2013 .

[9]  Chunxiang Wang,et al.  Research on precision tension control system based on neural network , 2004, IEEE Trans. Ind. Electron..

[10]  Pramod R Raul,et al.  Design and implementation of adaptive PI control schemes for web tension control in roll-to-roll (R2R) manufacturing. , 2015, ISA transactions.

[11]  Qiang Li,et al.  Study of wire tension control system based on closed loop PID control in HS-WEDM , 2016 .

[12]  LiuQiang,et al.  Data-Based Hybrid Tension Estimation and Fault Diagnosis of Cold Rolling Continuous Annealing Processes , 2011 .

[13]  Zhihuan Zhang.  Fault tolerant control for the web tension system , 2007, 2007 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[14]  Jiayin Zang,et al.  Nonlinear control of triple inverted pendulum based on GA–PIDNN , 2015 .

[15]  Mulan Wang,et al.  Model Reference Adaptive Tension Control of Web Packaging Material , 2008, 2008 International Conference on Intelligent Computation Technology and Automation (ICICTA).

[16]  Chun-yu Jia,et al.  Modeling and Simulation of Hydraulic Roll Bending System Based on CMAC Neural Network and PID Coupling Control Strategy , 2013 .

[17]  Myeong-Kwan Park,et al.  Tension control of wire rope in winch spooler using magneto rheological brake , 2016 .

[18]  M. Valipour.  Optimization of neural networks for precipitation analysis in a humid region to detect drought and wet year alarms , 2016 .

[19]  Hong Ya Fu,et al.  A Review of Tensioner for Automated Fiber Placement , 2013 .

[20]  Takashi Imamura,et al.  MODELING AND TENSION CONTROL OF FILAMENT WINDING PROCESS , 2002 .

[21]  Ji Wengang,et al.  Research on Constant-Tension Control Based on Fuzzy Multiple Models , 2008, 2008 International Symposium on Computational Intelligence and Design.

[22]  Hua Shu,et al.  Application of additional momentum in PID neural network , 2014, 2014 4th IEEE International Conference on Information Science and Technology.

[23]  Kazuhiro Yubai,et al.  Correlation-based direct tuning of MIMO controllers by least-squares and its application to tension-and-speed control apparatus , 2009, 2009 ICCAS-SICE.

[24]  Kyung Hyun Choi,et al.  Fuzzy decoupling to reduce propagation of tension disturbances in roll-to-roll system , 2014 .

[25]  Seshadhri Srinivasan,et al.  Design of PSO-Based PI Controller for Tension Control in Web Transport Systems , 2016 .

[26]  Zou Zheng.  Structural Design and Control System of Number Control Machine for Stranded Wires Helical Spring , 2009 .

[27]  Kiyoshi Ohishi,et al.  Analysis of interaction force of wire-based robot using variable wire rope tension control , 2009, 2009 35th Annual Conference of IEEE Industrial Electronics.

[28]  Tommy W. S. Chow,et al.  A recurrent neural-network-based real-time learning control strategy applying to nonlinear systems with unknown dynamics , 1998, IEEE Trans. Ind. Electron..