Smart Systems for Industrial Applications. Группа авторов

J., Smith, D., Jamalipour, A., Wireless Body Area Networks: A Survey. IEEE Commun. Surv. Tutor., 16, 3, 1658–1686, 2014.

      22. Rodrigues, J.J.P.C. et al., Enabling Technologies for the Internet of Health Things. IEEE Access, 6, 13129–13141, 2018.

      23. Ooi, P., Culjak, G., Lawrence, E., Wireless and wearable overview: stages of growth theory in medical technology applications. International Conference on Mobile Business (ICMB’05), IEEE, 2005.

      24. Khalid, H. et al., A comprehensive review of wireless body area network. J. Netw. Comput. Appl., 143, 178–198, 2019.

      25. Al-Janabi, S. et al., Survey of main challenges (security and privacy) in wireless body area networks for healthcare applications. Egypt. Inform. J., 18, 2, 113–122, July 2017.

      26. Sangita Singh, S., Artificial Intelligence and the Internet of Things in Healthcare, Healthcare and Life Sciences, 2018, accessed 6 April 2018, https://thejournalofmhealth.com/artificial-intelligence-and-the-internet-of-thingsin-healthcare.

      27. Azimi, I. et al., HiCH: Hierarchical Fog-Assisted Computing Architecture for Healthcare IoT. ACM Trans. Embed. Comput. Syst., 16, 5s, 1–20, Sept. 2017.

      28. Baskar, S., A dynamic and interoperable communication framework for controlling the operations of wearable sensors in smart healthcare applications. Comput. Commun., 149, 17–26, Jan. 2020.

      29. Deepak, B.D., Al-Turjman, F., Aloqaily, M., Alfandi, O., An Authentic-Based Privacy Preservation Protocol for Smart e-Healthcare Systems in IoT. IEEE Access, 7, 135632–135649, 2019.

      30. Bejnordi, B.E., Veta, M., van Diest, P.J. et al., Diagnostic Assessment of deep learning algorithms for detection of lymph node metas-tases in women with breast cancer. JAMA, 318, 2199–2210, 2017.

      31. Saba, L., Biswas, M., Kuppili, V. et al., The present and future of deep learning in radiology. Eur. J. Radiol., 114, 14–24, 2019.

      32. Francis, N.K., Luther, A., Salib, E. et al., The use of artificial neural networks to predict delayed discharge and readmission in enhanced recovery following laparoscopic colorectal cancer surgery. Tech. Coloproctol., 19, 419–428, 2015.

      33. Rabbani, M., Kanevsky, J., Kafi, K. et al., Role of artificial intelligence in the care of patients with non small cell lung cancer. Eur. J. Clin. Invest., 48, 1–7, 2018.

      34. Obrzut, B., Kusy, M., Semczuk, A. et al., Prediction of 5-year overall survival in cervical cancer patients treated with radical hysterectomy using computational intelligence methods. BMC Cancer, 17, 840, 2017.

      35. Murugesan, Y.P., Alsadoon, A., Manoranjan, P., Prasad, P.W.C., A novel rotational matrix and translation vector algorithm: geometric accuracy for augmented reality in oral and maxillofacial surgeries. Int. J. Med. Robot., 14, e1889, 2018.

      36. Bourdel, N., Collins, T., Pizarro, D. et al., Augmented reality in gynecologic surgery: evaluation of potential benefits for myomectomy in an experimental uterine model. Surg. Endosc., 31, 456–461, 2017.

      37. Mendivil, A.A., Abaid, L.N., Brown, J.V. et al., The safety and feasibility of minimally invasive sentinel lymph node staging using indocyanine green in the manage-ment of endometrial cancer. Eur. J. Obstet. Gynecol. Reprod. Biol., 224, 29–32, 2018.

      38. Waran, V., Narayanan, V., Karuppiah, R. et al., Utility of multi material 3D printers in creating models with pathological entities to enhance the training experience of neurosurgeons. J. Neurosurg., 120, 489–492, 2014.

      1 *Corresponding author: [email protected]

      2

      Pneumatic Position Servo System Using Multi-Variable Multi-Objective Genetic Algorithm–Based Fractional-Order PID Controller

       D.Magdalin Mary1*, V.Vanitha2 and G.Sophia Jasmine1

       ¹ Department of Electrical and Electronics Engineering Sri Krishna College of Technology, Coimbatore, Tamilnadu, India ² Department of Electrical and Electronics Engineering, VSB College of Engineering Technical Campus, Coimbatore, Tamilnadu, India

       Abstract

      In the last few decades, pneumatic servo systems are gaining popularity in numerous industrial applications because of numerous benefits such as high power to volume ratio, high rapidity, less economic, and easy maintenance plus long life. Servo pneumatic positioning systems have proven to be more cost effective than hydraulic systems because of the availability of air in abundance. In the pneumatic system, mid-air pump is consumed to supply the compressed air by regulating the proportional valve slots and drive the piston connected to the payload. Proportional integral differential (PID) controller is able to compensate the nonlinearity, and its performance becomes unsatisfactory when the system conditions change. The fractional-order PID (FOPID) controllers are robust and accurate than conventional PID controllers as they have two additional parameters for tuning. In this work, the fractional order of pneumatic servo system is used in the model of air pump and FOPID is propositioned to control the position of valve. The way to progress its performance, the controller parameters are optimized using genetic algorithm (GA). Proposed algorithm is validated for different reference positions and various values of evolution parameters define the system performances and give the optimized solutions in all aspects.

      Keywords: Pneumatic position servo system, FOPID, GA, MATLAB, PIC microcontroller

2.1 Introduction

      The flexibility of proportional integral differential (PID) controller is less, when the reference and other conditions of the system change considerably. The system has the following advantages as easy of maintenance, spotlessness, PWR, and modest assembly which has been used broadly in automation application as food industries, medical, mechatronics, and bio-engineering. Due to essential compressibility of airflow through orifice valve in cylinder, movement of piston based on the position, variation of system parameters yields a nonlinear system with uncertainties. In nonlinear PID (NPID) controllers, the variation of nonlinear gain is exploited for greater accuracy. Literatures show that fractional-order PID (FOPID) controller, which combines the concept of fractional system theory and integer-type PID (IPID) controller gives better response than standard PID controller. But the tuning of controller parameters in FOPID is tougher than IPID. If these parameters are not tuned accurately, then the system performance will be poor [2, 10]. Many optimization techniques such as GA, MFA, and PSO are used to tune the parameters of FOPID to improve the system response [11, 12]. The numerous governing techniques are proposed for pneumatic control system as PID controller, robust control, sliding mode control. Due to its reliability and control mechanism, FOPID control is commonly used in industries [18]. The implementation of PID are widely used in ON/OFF solenoid valve position which includes constrained integral term, forward loop position, compensation of friction element, and the performance indices of the function compare with the solenoid valve. The flexibility in PID controller is reduces due to its nonlinearity. In NPID controller, the variation of nonlinear gain is exploited for greater accuracy. In recent days, the numbers of intelligent control techniques are developed to progress the accuracy of the system with trajectory tracking. Neural control–based PID has the proposed compensation under various load operating conditions used to get optimized design in PID controllers.

The sliding mode adaptive control provides the stability in system parameters to achieve desire performance