電動跑步機由於不受到氣候環境、場地等一些因素的約制，為一種便捷的有氧健身器材而受到青睞。心跳速率為人體關鍵性生理指標，若能確切監測心率數值，可避免不必要的運動傷害及有效地反應鍛煉效果，因而跑步機逐漸由被動的心率監測往主動的心率控制方向發展。本論文以電動跑步機運動者心率控制系統為研究目標，完成電動機無感測器調速系統設計、跑步機心率與血氧濃度監測裝置和心率控制策略發展等任務。從理論分析到軟硬體實現，闡述電動跑步機運動者心率控制系統的設計過程。
本論文主要分為三大部分，其內容第一部份為針對運動者生理參數監測裝置之研製，以監測其心跳速率及血氧濃度。由於目前市面上的指尖式血氧計(Oximeter)受限於穿戴位置而不便於長期監測，尤其是在運動情況下。因此，本論文將發展戒指型血氧計以克服此問題，透過光學人體組織模擬來找出最佳光源以及檢測器的放置位置，並使用一拋物線反射鏡增強光源訊號，經由模擬分析結果驗證其可行性。
論文第二部份為跑步機心率控制法則設計開發。由於心率控制的準確性深受系統的參數變化、人員身心狀況等不確定項的影響。因此，本論文提出一以遞迴式模糊類神經網路(Recurrent fuzzy neural network, RFNN)為基礎的心率控制器，可自動調節跑步機速度及坡度，使心率準確追隨所設定心率標準值，透過RFNN來解決非線性系統的追蹤控制問題，最後使用李亞譜諾夫穩定定理 (Lyapunov stability theorem)來驗證網路參數的收斂性，以便取得最佳的學習率與收斂速度，增進心率追隨效能與穩定性。
論文第三部份為馬達驅動控制技術之研究。本研究針對磁場導向控制(Field-oriented control)的感應馬達無感測器驅動系統，提出一個基於模糊類神經網路估測器用來估測轉子磁通與轉速，由於直接量測馬達磁通是相當不易且馬達電氣參數容易隨溫度環境而變化，因此設計一具自我調適且快速即時學習能力之模糊類神經網路磁通估測器，在面對馬達參數不確定性與負載變動時具有較佳的強健性，將系統動態數學模型所計算轉子磁通和估測轉子磁通之誤差，採用最深梯度法(Steepest descent algorithm)和倒傳遞法(Back propagation)去調整模糊類神經網路之參數，並以李亞譜諾夫穩定定理來確保系統之穩定性。

Electric treadmill is one of the most popular health-training equipments and has a great market prospect．Development of a multi-functional and high value-added electric treadmill is of great realistic significance．As heart rate can be used as a measure of exercise intensity, controlling HR should allow for the proper control of exercise intensity during treadmill exercise. The major aim of this dissertation is to develop the heart control techniques of a motorized treadmill system, which involve with the measure and control of heart rate (HR) and the motor driving control for treadmill exercise.
The first part of this dissertation deals with the problem of monitoring physiological states of exercisers. As accurate measurement of heart rate is becoming increasingly important during exercise, many monitors have become commercially available. The majority of these devices use an infrared source and a transistor photo-detector for measuring the pulse. Excluding heart rate monitor of chest straps, transcutaneous pulse oximeters are being widely used for non-invasive simultaneous assessment of hemoglobin oxygen saturation so as to estimate heart rate at rest and during exercise. Fingertip-type pulse oximeters are popular, but their inconvenience for fierce movement. Therefore, it is necessary to develop other types of pulse oximeters, such as ring-type pulse oximeters. This study used human tissue simulations to evaluate the practicability of a ring-type reflection pulse oximeter design. Moreover, given that the collection of diffusely reflected light can be enhanced by using a parabolic reflector, the efficacy of a ring-type refection pulse oximeter with a parabolic reflector was also evaluated.
The second part of this dissertation deals with the HR regulation during treadmill exercise. A recurrent fuzzy neural network (RFNN) control framework was applied to regulate HR during treadmill exercise. The recurrent fuzzy neural network heart rate controller (RFNNHRC) combines a fuzzy reasoning capability to accommodate uncertain information and an artificial recurrent neural network learning process that corrects for treadmill system nonlinearities and uncertainties. Treadmill speed and incline are controlled by the RFNNHRC to achieve minimal heart rate deviation from a pre-set profile using adjustable parameters and an on-line learning algorithm that provides robust performance against parameter variations.
The third part of this dissertation is focused on the motor drive control techniques for treadmill speed regulation. In motor speed control system, a shaft encoder was widely used to obtain the speed information. However, speed sensors have several disadvantages from the drive cost, noise immunity and reliability viewpoints. In addition, for some special applications (such as very high speed motor drives) difficulties were encountered in mounting these speed sensors. Accordingly, sensorless control techniques for motor drive system have been a research topic in recent decades. This study proposes the practical methods for sensorless speed control of induction motor (IM). In IM drive system, a speed estimation algorithm based on the fuzzy neural network is proposed for IM speed sensorless control. The speed estimation is based on rotor flux deduction and estimated rotor flux, calculated using a fuzzy neural network. The fuzzy neural network is a four-layer network. The steepest descent algorithm is used to adjust the fuzzy neural network parameters to minimize the error between the rotor flux and estimated rotor flux, enabling precise rotor speed estimation.
The benefit of the developed treadmill control system not only could assist patients in cardiovascular rehabilitation and therapy to safely control the heart rate following a suitable profile, but also allow general users to optimize their training intensity in athletics and fitness applications.

[1]M. I. Lambert, Z. H. Mbambo and A. C. Gibson, “Heart rate during training and competition for long-distance running,” Sports Sciences, vol 16, pp 85–90, 1998.
[2]J. Achten and A. E. Jeukendrup, “Heart rate monitoring: Applications and limitations,” Sports Med., vol. 33, no. 7, pp. 517–538, 2003.
[3]T. M. Cheng, A. V. Savkin, B. G. Celler, and S. W. Su, “Nonlinear modeling and control of human heart rate response during exercise with various work load intensities,” IEEE Trans. Biomed. Eng., vol. 55, no. 11, pp. 2499–2508,2008.
[4]H. Saito and T. Togawa, “Open-loop control to achieve linear heart rate increase in the treadmill exercise test,” in proceedings of IEEE Engineering in Medicine and Biology Society 20th Annual Conference, vol. 20, no. 5, 1998.
[5]S. W. Su, B. G. Celler, A. V. Savkin, H. T. Nguyen, T. M. Cheng, Y. Guo, and L. Wang, “Transient and steady state estimation of human oxygen uptake based on noninvasive portable sensor measurements,” Med. Biol. Eng. Comput., vol. 47, no.10, pp. 1111-1117, 2009.
[6]M. Fairbarn, S. Blackie, N. McElvaney, B. Wiggs, P. Pare, and R. Pardy, “Prediction of heart rate and oxygen uptake during incremental and maximal exercise in healthy adults,” Chest, vol.105, pp.1365-1369, 1994.
[7]S. Su, L. Wang, B. Celler, E. Ambikairajah, and A. Savkin, “Estimation of walking energy expenditure by using support vector regression,” In proceedings of the 27th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), Shanghai, China, pp. 3526-3529, 2005.
[8]P. Astrand, T. Cuddy, B. Saltin, and J. Stenberg, “Cardiac output during submaximal and maximal work,” J. Appl. Physiol, vol. 9, pp. 268-274, 1964.
[9]M. Freedman, G. Snider, P. Brostoff, S. Kimelblot, and L. Katz, “Effects of training on response of cardiac output to muscular exercise in athletes,” J. Appl. Physiol., vol.8, pp. 37-47, 1955.
[10]A. L. Ries, P. F. Fedullo, and J. L. Clausen, “Rapid changes in arterial blood gas levels after exercise in pulmonary patients,” Chest, vol. 83, pp.454-458, 1983
[11]Y. Lyriboz, S. Powers, J. Morrow, D. Ayers and G. Landry, “Accuracy of pulse oximeters in estimating heart rate at rest and during exercise,” British Journal of Sports Medicine, vol.25, no. 3, pp.162-164, 1991.
[12]H. H. Asada, P. Shaltis, A. Reisner, S. Rhee, and R. C. Hutchinson, “Mobile monitoring with wearable photoplethysmographic biosensors,” IEEE Engineering in Medicine and Biology Magazine, vol. 22, pp. 28–40, 2003.
[13]B. Venema, N. Blanik, V. Blazek, H. Gehring, A. Opp, and S. Leonhardt, “Advances in reflective oxygen saturation monitoring with a novel in-ear sensor system: results of a human hypoxia study,” IEEE Transactions on Biomedical Engineering, vol.59, , pp.2003–2010, 2012.
[14]J. B. Forsyth, T. L. Martin, D. Young-Corbett, and E. Dorsa, “Feasibility of intelligent monitoring of construction workers for carbon monoxide poisoning,” IEEE Transactions on Automation Science and Engineering, vol. 9, pp.505–515, 2012.
[15]S. Su, S. Huang, L. Wang, B. Celler, A. Savkin, and Y. Guo, “Optimizing heart rate regulation for safe exercise,” Ann. Biomed. Eng., vol. 38, pp.758–68, 2010.
[16]S. Scalzi, P. Tomei, and C. Verrelli, “Nonlinear control techniques for the heart rateregulation in treadmill exercises,” IEEE Trans. Biomed. Eng., vol. 59, pp. 599–603, 2012.
[17]L. Jamieson, K. Hunt, and D. Allan, “A treadmill control protocol combining nonlinear,equally smooth increases in speed and gradient: exercise testing for subjectswith gait and exercise limitations optimizing heart rate regulation for safeexercise,” Med. Eng. Phy., vol. 30, pp. 747–54, 2008.
[18]K. J. Hunt, “Treadmill control protocols for arbitrary work rate profiles combiningsimultaneous nonlinear changes in speed and angle,” Biomed Signal Process Cont., vol.3, pp.278–82, 2008.
[19]K. Weng, B. Turk, L. Dolores, T. Nguyen, B. Celler, S. Su, et al., “Fast tracking of a given heart rate profile in treadmill exercise,” In Proceedings of the 32th annual international conference of engineering in medicine and biology society (EMBS), pp. 2569–2572, 2010.
[20]T. M. Cheng, A. V. Savkin, B. G. Celler, and S. W. Su, “Nonlinear modeling and control of human heart rate response during exercise with various work load intensities,” IEEE Trans. Biomed. Eng., vol. 55, no. 11, pp. 2499–2508,2008.
[21]S. W. Su, L. Wang, B. G. Celler, A. V. Savkin, and Y. Guo, “ Identification and control for heart rate regulation during treadmill exercise,” IEEE Transactions on Biomedical Engineering, vol. 54, no. 7, pp. 1238–1246, 2007.
[22]A. Alessandri, C. Cervellera and M. Sanguineti, “Design of asymptotic estimators: an approach based on neural networks and nonlinear programming,” IEEE Trans. on Neural Networks, vol. 18, no. 1, pp. 86-96, 2007.
[23]M. Liu, “Delayed standard neural network models for control systems,” IEEE Trans. on Neural Networks, vol. 18, no. 5, pp. 1376-1391, 2007.
[24]R. H. Abiyev and O. Kaynak, “Fuzzy wavelet neural networks for identification and control of dynamic plants-A novel structure and a comparative study,” IEEE Trans. on Industrial Electronics, vol. 55, no.8, pp. 3133-3140, 2008.
[25]C. M. Lin and C. F. Hsu, “Recurrent-neural-network-based adaptive-backstepping control for induction servomotors,” IEEE Trans. on Industrial Electronics, vol. 52, no. 6, pp. 1677-1684, 2005.
[26]C. C. Ku and K. Y. Lee, “Diagonal recurrent neural networks for dynamic systems control,” IEEE Trans. on Neural Networks, vol. 6, no. 1, pp. 144-156, 1995.
[27]D. G. Stavrakouds and J. B. Theochairs, “Pipelined recurrent fuzzy neural networks for nonlinear adaptive speech prediction,” IEEE Trans. on Systems, Man and Cybernetics, Part B: Cybernetics, vol. 37, no. 5, pp. 1305-1320, 2007.
[28]F. J. Lin, C. H. Lin, and P. K. Huang, “Recurrent fuzzy neural network controller design using sliding-mode control for linear synchronous motor drive,” IEE Control Theory Appl., vol. 151, no. 4, pp. 407-416, Jul. 2004.
[29]F. J. Lin, R. J. Wai, K. K. Shyu, and T. M. Liu, “Recurrent fuzzy neural network control for piezoelectric ceramic linear ultrasonic motor drive,” IEEE Trans. Ultrason., Ferroelectr., Freq. Control, vol. 48, no. 4, pp. 900-913, Jul. 2001.
[30]C. J. Lin and C. H. Chen, “Identification and prediction using recurrent compensatory neuro-fuzzy systems,” Fuzzy Sets and Systems, vol. 150, no. 2, pp. 307-330, 2005.
[31]A. M. Garcıa, T. A. Lipo and D. W. Novotny, “A New Induction Motor V/f Control Method Capable of High-Performance Regulation at Low Speeds,” IEEE Transactions on Industry Applications, vol. 34, no. 4, pp. 813-821, 1998.
[32]P. D. C. Perera, F. Blaabjerg, J. K. Pedersen and P. Thogersen, “A Sensorless Stable V/f Control Method for Permanent-Magnet Synchronous Motor Drives,” IEEE Transactions on Industry Applications, vol. 39, no. 3, pp. 783-791, 2003.
[33]G. K. Singh, D. K. P. Singh, K. Nam and S. K. Lim, “A Simple Indirect Field-Oriented Control Scheme for Multiconverter-fed Induction Motor,” IEEE Transactions on Industrial Electronics, vol. 52, no. 6, pp. 1653-1659, 2005.
[34]A. Consoli, G. Scarcella and A. Testa, “Slip-Frequency Detection for Indirect Field-Oriented Control Drives,” IEEE Transactions on Industry Applications, vol. 40, no. 1, pp. 194-201, 2004.
[35]M. M. Bech, J. K. Pedersen and F. Blaabjerg, “Field-Oriented Control of an Induction Motor Using Random Pulse-Width Modulation,” IEEE Transactions on Industry Applications, vol. 37, no. 6, pp. 1777-1785, 2001.
[36]G. Diana and R.G. Harley, “An Aid for Teaching Field Oriented Control Applied to Induction Machines,” IEEE Transactions on Power System, vol. 4, no. 3, pp. 1258-1286, 1989.
[37]Y. A. Kwon and S. H. Kim, “A New Scheme for Speed-Sensorless Control of Induction Motor,” IEEE Transactions on Industrial Electronics, vol. 51, no. 3, 2004.
[38]J. Salomaki, M. Hinkkanen, and J. Luomi, “Sensorless Control of Induction Motor Drives Equipped with Inverter Output Filter,” IEEE Transactions on Industrial Electronics, vol. 53, no. 4, 2006.
[39]T. S. Kwon, M. H. Shin and D. S. Hyun, “Speed Sensorless Stator Flux-Oriented Control of Induction Motor in the Field Weakening Region Using Luenberger Observer,” IEEE Transactions on Power Electronics, vol. 20, no. 4, pp. 864-869, 2005.
[40]Y. A. Kwon and S. H. Kim, “A New Scheme for Speed-Sensorless Control of Induction Motor,” IEEE Transactions on Industrial Electronics, vol. 51, no. 3, pp. 545-550, 2004.
[41]M. Saejia and S. Sanwongwanich, “Averaging Analysis Approach for Stability Analysis of Speed-Sensorless Induction Motor Drives With Stator Resistance Estimation,’’ IEEE Transactions on Industrial Electronics, vol. 53, no. 1, pp. 162-177, 2006.
[42]Y. R. Kim, S. K. Sul and M. H. Park, “Speed Sensorless Vector Control of Induction Motor Using Extended Kalman Filter,” IEEE Transactions on Industry Applications, vol. 30, no. 5, pp. 1125-1233, 1994.
[43]L. Zhen and L. Xu, “Sensorless Field Orientation Control of Induction Machines Based on a Mutual MRAS Scheme,” IEEE Transactions on Industrial Electronics, vol. 45, no. 5, pp. 824-831, 1998.
[44]C. Lascu, I. Boldea and F. Blaabjerg, “Direct Torque Control of Sensorless Induction Motor Drives: a Sliding-Mode Approach,” IEEE Transactions on Industry Applications, vol. 40, no. 2, pp. 582-590, 2004.
[45]T. C. Chen and C. H. Yu, “Motion Control with Deadzone Estimation and Compensation Using GRNN for TWUSM Drive System,” Expert Systems with Applications, vol. 36, pp. 10931–10941, 2009.
[46]T. C. Chen, T. J. Ren and Y. W. Lou, “Ultrasonic Motor Control Based on Recurrent Fuzzy Neural Network Controller and General Regression Neural Network Controller,” Computational Intelligence, vol. 465, pp. 291-305, 2013.
[47]J. Peng and R. Dubay, “Identification and Adaptive Neural Network Control of a DC Motor System with Dead-zone Characteristics,” ISA Transactions, vol. 50, pp. 588–598, 201.
[48]A. Alessandri, C. Cervellera and M. Sanguineti, “Design of Asymptotic Estimators: An Approach Based on Neural Networks and Nonlinear Programming,” IEEE Trans. on Neural Networks, vol. 18, no. 1, pp. 86-96, January 2007.
[49]S. E. Shafiei1 and M. R. Soltanpour, “Neural Network Sliding-mode-PID Controller Design for Electrically Driven Robot Manipulators,” International Journal of Innovative Computing, Information and Control, vol. 7, no. 2, February 2011, pp. 511-524.
[50]S. H. Kim, T. S. Park, J. Y Yoo, G. T. Park, “Speed-Sensorless Vector Control of an Induction Motor Using Neural Network Speed Estimation,” IEEE Transaction on Industrial Electronics, vol. 48, no. 3, pp. 609-614, 2001.
[51]T. C. Chen, T. J. Ren and Y. W. Lou, “Design of Recurrent Fuzzy Neural Network and General Regression Neural Network Controller for Traveling-wave Ultrasonic Motor,” International Conference on Neural Computation Theory and Applications (NCTA2011), Paris, France, Oct. 24-26, 2011.
[52]R. Cubeddu, A. Pifferi, P. Taroni, A. Torricelli, and G. Valentini, “Noninvasive absorption and scattering spectroscopy of bulk diffusive media: an application to the optical characterization of human breast,” Applied Physics Letters, vol. 74, pp. 874–876, 1999.
[53]G. Zonios, U. Shankar, and V. K. Iyer, “Pulse oximetry theory and calibration for low saturations,” IEEE Transactions on Biomedical Engineering, vol. 51, pp.818–822, 2004.
[54]S. Reichelt, J. Fiala, A. Werber, K. Forster, C. Heilmann, R. Klemm, and H. Zappe, “Development of an implantable pulse oximeter,” IEEE Transactions on Biomedical Engineering, vol. 55, pp. 581–588, 2008.
[55]K. Urpalainen, “Development of a fractional multi-wavelength pulse oximeter algorithm,” Master’s dissertation, Aalto University, Finland, pp.1–72, 2011.
[56]R. Graaff, A. C. M. Dassel, M. H. Koelink, F. F. M. de Mul, J. G. Aarnoudse, and W. G. Zijistra, “Optical properties of human dermis in vitro and in vivo,” Applied Optics, vol. 32, pp.435–447, 1993.
[57]V. V. Tuchin, “Light scattering study of tissues,” Physics-Uspekhi, vol. 40, pp.495–515, 1997.
[58]M. P. McEwen, G. P. Bull, and K. J. Reynolds, “Vessel calibre and haemoglobin effects on pulse oximetry,” Physiological Measurement, vol. 30, pp.869–883, 2009.
[59]S. J. Erickson, J. B. Kneeland, W. D. Middleton, A. Jesmanowicz, J. Hyde, T. L. Lawson, and W. D. Foley, “MR imaging of the finger: correlation with normal anatomic sections,” American Journal of Roentgenology, vol.152, pp.1013–1019, 1989.
[60]Z. Krawiecki, A. Cysewska-Sobusiak, G. Wiczynski, and A. Odon, “Modeling and measurements of light transmission through human tissues,” Bulletin of the Polish Academy of Sciences—Technical Science, vol. 56, pp. 147–154, 2008.
[61]D. J. Faber, M. C. G. Aalders, E. G. Mik, B. A. Hooper, M. J. C. van Gemert, and T. G. van Leeuwen, “Oxygen saturation-dependent absorption and scattering of blood,” Physical Review Letters, vol. 93, pp.028102-1–028102-4, 2004.
[62]A. N. Bashkatov, D. M. Zhestkov, E. A. Genina, and V. V. Tuchin, “Immersion clearing of human blood in the visible and near-infrared spectral regions,” Optics and Spectroscopy, vol. 98, pp. 638–646, 2005.
[63]H. F. Ding, J. Q. Lu, W. A. Wooden, P. J. Kragel, and X. H. Hu, “Refractive indices of human skin tissues at eight wavelengths and estimated dispersion relations between 300 and 1600 nm,” Physics in Medicine and Biology, vol. 51,pp.1479–1489, 2006.
[64]O. Zhernovaya, O. Sydoruk, V. Tuchin, and A. Douplik, “The refractive index of human hemoglobin in the visible range,” Physics in Medicine and Biology, vol. 56, pp.4013–4021, 2011.
[65]G. J. Langewouters, A. Zwart, R. Busse, and K. H. Wesseling, “Pressure-diameter relationships of segments of human finger arteries,” Clinical Physics and Physiological Measurement, vol. 7, pp.43–56, 1986.
[66]V. A. Peris and S. Hu, “Validation of a Monte Carlo platform for the optical modelling of pulse oximetry,” Journal of Physics: Conference Series, vol. 85, pp. 012027-1–012027-6, 2007.