By Derong Liu, Qinglai Wei, Ding Wang, Xiong Yang, Hongliang Li
This booklet covers the newest advancements in adaptive dynamic programming (ADP). The textual content starts off with an intensive heritage assessment of ADP with the intention that readers are sufficiently conversant in the basics. within the middle of the publication, the authors tackle first discrete- after which continuous-time platforms. assurance of discrete-time structures starts off with a extra basic kind of price generation to illustrate its convergence, optimality, and balance with entire and thorough theoretical research. A extra sensible type of price generation is studied the place worth functionality approximations are assumed to have finite mistakes. Adaptive Dynamic Programming additionally information one other road of the ADP technique: coverage generation. either simple and generalized types of policy-iteration-based ADP are studied with entire and thorough theoretical research when it comes to convergence, optimality, balance, and mistake bounds. between continuous-time structures, the keep watch over of affine and nonaffine nonlinear platforms is studied utilizing the ADP method that's then prolonged to different branches of regulate idea together with decentralized keep watch over, powerful and warranted rate regulate, and online game thought. within the final a part of the booklet the real-world importance of ADP idea is gifted, concentrating on 3 software examples constructed from the authors’ work:
• renewable strength scheduling for clever energy grids;• coal gasification strategies; and• water–gas shift reactions.
Researchers learning clever keep watch over tools and practitioners seeking to practice them within the chemical-process and power-supply industries will locate a lot to curiosity them during this thorough therapy of a sophisticated method of control.
Read Online or Download Adaptive Dynamic Programming with Applications in Optimal Control PDF
Similar robotics & automation books
Strong regulate of Robots bridges the space among strong keep watch over conception and purposes, with a unique specialize in robot manipulators. it's divided into 3 parts:robust regulate of standard, fully-actuated robot manipulators;robust post-failure keep an eye on of robot manipulators; androbust keep an eye on of cooperative robot manipulators.
The atomic strength microscope (AFM) has been effectively used to accomplish nanorobotic manipulation operations on nanoscale entities corresponding to debris, nanotubes, nanowires, nanocrystals, and DNA for the reason that Nineties. there were many development on modeling, imaging, teleoperated or computerized keep an eye on, human-machine interfacing, instrumentation, and purposes of AFM dependent nanorobotic manipulation platforms in literature.
''Using a pragmatic process that comes with in basic terms beneficial theoretical heritage, this booklet specializes in utilized difficulties that inspire readers and aid them comprehend the suggestions of automated regulate. The textual content covers servomechanisms, hydraulics, thermal regulate, mechanical platforms, and electrical circuits.
- Engineering vibration analysis with application to control systems
- Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles
- Robust Stability and Convexity
- Variable Structure Systems: From Principles to Implementation (IEE Control Engineering)
- Autonomous Tracked Robots in Planar Off-Road Conditions: Modelling, Localization, and Motion Control
- Robot Building for Beginners
Additional info for Adaptive Dynamic Programming with Applications in Optimal Control
Leake RJ, Liu RW (1967) Construction of suboptimal control sequences. SIAM J Control 5(1):54–63 38. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444 39. Lendaris GG, Paintz C (1997) Training strategies for critic and action neural networks in dual heuristic programming method. In: Proceedings of the IEEE international conference on neural networks, pp 712–717 References 29 40. Lewis FL, Liu D (2012) Reinforcement learning and approximate dynamic programming for feedback control.
Int J Robust Nonlinear Control 9:1071–1096 22. Dalton J, Balakrishnan SN (1996) A neighboring optimal adaptive critic for missile guidance. Math Comput Model 23:175–188 23. Dreyfus SE, Law AM (1977) The art and theory of dynamic programming. Academic Press, New York 24. Enzenberger M (2004) Evaluation in Go by a neural network using soft segmentation. In: Advances in computer games - many games, many challenges (Proceedings of the advances in computer games conference), pp 97–108 25. Fu ZP, Zhang YN, Hou HY (2014) Survey of deep learning in face recognition.
The model network in Fig. 1); it can be trained previously offline [79, 128], or trained in parallel with the critic and action networks . After the model network is obtained, the critic network will be trained. The critic network gives an estimate of the cost function. 6), for which many standard NN training algorithms can be utilized [29, 146]. Note that in Fig. 1, ˆ xk+1 , Wc ) is an approximation to the cost the output of the critic network Jˆk+1 = J(ˆ function J at time k + 1, where xˆ k+1 is not a real trajectory but a prediction of the states from the model network.