传统的自动控制方法因为其固定参数等弊端极大限制了控制效果，生物智能算法因为其环境自适应与自学习机制的特性，为突破传统控制方法的瓶颈提供了一种新的思路，并且随着强化学习等机器学习理论与方法的不断完善与发展，生物智能算法的性能也得到了极大的提高。总结了在智能控制中常用的7种生物智能算法，分析了经典的自动控制方法与生物智能算法，尤其是强化学习、深度学习等新型智能算法的结合的应用实例。结合近年来兴起的深度学习，强化学习及类脑智能科学对智能控制的发展现状，以及未来的发展趋势进行展望。强调一种智能辅助控制方法，将智能算法与传统控制方法相结合，为智能控制的研究提供新的思路与实用范例。
The classical control methods have shortcoming,, such as its fixed parameters, with a limited control effect, and the Biological Intelligence Algorithm provides a new way to break the bottleneck of the classical control methods because of its adaptive and learning mechanism. With the improvement of the theory of the reinforcement learning and the deep learning, the performance of the Biological Intelligence Algorithm is greatly improved. This paper reviews seven kinds of intelligent algorithms commonly used in intelligence control, and the application examples of combining the classical automatic control methods and the intelligent algorithms, especially, the reinforcement learning. The development status and the future development trend of the intelligent control based on the reinforcement learning, the deep learning and the Brain-inspired Intelligence Technology in recent years are discussed. The purpose of this paper is to emphasize a new idea of combining the intelligent algorithms with the classical control methods, and provide some new ideas and practical examples for the intelligent control.
[1] Åström K J,McAvoy T J. Intelligent control[J]. Journal of Process Control, 1992, 2(3):115-127.
[2] Das S K. Modeling intelligent decision-making command and control agents:An application to air defense[J]. IEEE Intelligent Systems, 2014, 29(5):22-29.
[3] Lecun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553):436-444.
[4] Huang Y N, Zhang A J, Hu M Y. Single Neuron PID control based on expert experiences for temperature difference control system of a digester[J]. Paper and Biomaterials, 2017, 2(1):52-58.
[5] Le T T, Huff T B, Cheng J X. Coherent anti-stokes raman scattering imaging of lipids in cancer metastasis[J]. BMC Cancer, 2009, 9(1):42-42.
[6] Ma J, Ni S, Xie W, et al. Deep auto-encoder observer multiple-model fast aircraft actuator fault diagnosis algorithm[J]. International Journal of Control Automation & Systems, 2017, 15(11):1-10.
[7] Liang X, Li Y, Dai C, et al. Reinforcement learningbased NOMA power allocation in the presence of smart jamming[J]. IEEE Transactions on Vehicular Technology, 2018, 67(4):3377-3389.
[8] Shi H, Li X, Hwang K S, et al. Decoupled visual servoing with fuzzy Q-Learning[J]. IEEE Transactions on Industrial Informatics, 2018, 14(1):241-252.
[9] Peng J I, Song A, Changcheng W U, et al. Human-robotrobot-cooperation based uncalibrated visual servoing control for mobile robotic manipulators without joint-state feedback[J]. Robot, 2017, 39(2):197-204.
[10] Zhao F, Yi Z, Wang G, et al. A brain-inspired decision making model based on top-down biasing of prefrontal cortex to basal ganglia and its application in autonomous UAV explorations[J]. Cognitive Computation, 2017, 10(6):1-11.
[11] He W, Chen Y, Yin Z. Adaptive neural network control of an uncertain robot with full-state constraints[J]. IEEE Transactions on Cybernetics, 2017, 46(3):620-629.
[12] Long W, Li X, Liang G, et al. A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2018, 65(7):5990-5998.
[13] Merayo N, Juárez D, Aguado J C, et al. PID controller based on a self-adaptive neural network to ensure QoS bandwidth requirements in passive optical networks[J]. IEEE/OSA Journal of Optical Communications & Networking, 2017, 9(5):433-445.
[14] Block H D. The perceptron:A model for brain functioning[J]. Reviews of Modern Physics, 1962, 35(1):123-134.
[15] Fan W, Li Z S. Prediction of the creep of piezoelectric ceramic based on BP neural network optimized by genetic algorithm[J]. Acta Metrologica Sinica, 2017, 38(4):429-434.
[16] Kuang Y, Singh R, Singh S, et al. A novel macroeconomic forecasting model based on revised multimedia assisted BP neural network model and ant colony algorithm[J]. Multimedia Tools & Applications, 2017, 76(18):1-22.
[17] Qian Y, Bi M, Tian T, et al. Very deep convolutional neural networks for noise robust speech recognition[J]. IEEE/ACM Transactions on Audio Speech & Language Processing, 2017, 24(12):2263-2276.
[18] Wang Y B, You Z H, Li X, et al. Predicting protein-protein interactions from protein sequences by a stacked sparse autoencoder deep neural network[J]. Molecular Biosystems, 2017, 13(7):1336-1344.
[19] Friedrich T, Kötzing T, Krejca M, et al. The compact genetic algorithm is efficient under extreme Gaussian noise[J]. IEEE Transactions on Evolutionary Computation, 2017, 21(3):477-490.
[20] Gosciniak I. Discussion on semi-immune algorithm behaviour based on fractal analysis[J]. Soft Computing, 2017, 21(14):3945-3956.
[21] Bonyadi M R, Michalewicz Z. Particle swarm optimization for single objective continuous space problems:A review[J]. Evolutionary Computation, 2017, 25(1):1-54.
[22] Majumder A, Laha D. Bacteria foraging optimization algorithm for robotic cell scheduling problem[J]. Materials Today Proceedings, 2017, 4(2):2129-2136.
[23] Liang X, Li Y, Dai C, et al. Reinforcement learningbased NOMA power allocation in the presence of smart jamming[J]. IEEE Transactions on Vehicular Technology, 2018, 67(4):3377-3389.
[24] Deng Y, Bao F, Kong Y, et al. Deep direct reinforcement learning for financial signal representation and trading[J]. IEEE Transactions on Neural Networks & Learning Systems, 2017, 28(3):653-664.
[25] Qiang Z, Yuan Q, Chao Z, et al. Missing data reconstruction in remote sensing image with a unified spatial-temporal-spectral deep convolutional neural network[J]. IEEE Transactions on Geoscience & Remote Sensing, 2018, 56(8):1-15.
[26] Zhao D, Liu D, Lewis F L, et al. Special issue on deep reinforcement learning and adaptive dynamic programming[J]. IEEE Transactions on Neural Networks & Learning Systems, 2018, 29(6):2038-2041.
[27] Serra P, Cunha R, Hamel T, et al. Landing of a quadrotor on a moving target using dynamic image-based visual servo control[J]. IEEE Transactions on Robotics, 2017, 32(6):1524-1535.
[28] Cong S, Liang Y. PID-like neural network nonlinear adaptive control for uncertain multivariable motion control systems[J]. IEEE Transactions on Industrial Electronics, 2009, 56(10):3872-3879.
