PID controllers are a standard building block in industrial control, and we have recently proposed automating the process of tuning the PID parameters to a particular plant, by means of neural networks. In order to as...
详细信息
PID controllers are a standard building block in industrial control, and we have recently proposed automating the process of tuning the PID parameters to a particular plant, by means of neural networks. In order to assess the performance of this new technique, we have built a real-time implementation, programmed in OCCAM and executed on INMOS transputers. A description is given of the main constituent blocks, with a special emphasis on the block which is responsible for the adaptation mechanism. The results obtained are presented for simulated plants with varying time-delay and varying number, and locations, of the poles.
Possible approaches for parallelism extraction in digital controller algorithms targeted at medium- to fine-grain parallel architectures are investigated. The methods use information on the node computation precedence...
详细信息
Possible approaches for parallelism extraction in digital controller algorithms targeted at medium- to fine-grain parallel architectures are investigated. The methods use information on the node computation precedence of realization structures expressed in the factored state variable description (FSVD). Three architectures are considered, namely a multiprocessor system, a systolic array and PACE, a novel architecture which can support structured and non-structured algorithms within a regular processor array. It is shown that this facility makes PACE particularly promising for the implementation of controller structures expressed in terms of the FSVD.
The field of intelligent control has recently emerged as a response to the challenge of controlling highly complex and uncertain nonlinear systems. It attempts to endow the controller with the key properties of adapta...
详细信息
ISBN:
(数字)9781447103196
ISBN:
(纸本)9781852334383;9781447110903
The field of intelligent control has recently emerged as a response to the challenge of controlling highly complex and uncertain nonlinear systems. It attempts to endow the controller with the key properties of adaptation, learn ing and autonomy. The field is still immature and there exists a wide scope for the development of new methods that enhance the key properties of in telligent systems and improve the performance in the face of increasingly complex or uncertain conditions. The work reported in this book represents a step in this direction. A num ber of original neural network-based adaptive control designs are introduced for dealing with plants characterized by unknown functions, nonlinearity, multimodal behaviour, randomness and disturbances. The proposed schemes achieve high levels of performance by enhancing the controller's capability for adaptation, stabilization, management of uncertainty, and learning. Both deterministic and stochastic plants are considered. In the deterministic case, implementation, stability and convergence is sues are addressed from the perspective of Lyapunov theory. When compared with other schemes, the methods presented lead to more efficient use of com putational storage and improved adaptation for continuous-time systems, and more global stability results with less prior knowledge in discrete-time sys tems.
This book introduces an optimal iterative learning control (ILC) design framework from the end user's point of view. Its central theme is the understanding of model dynamics, the construction of a procedure for sy...
详细信息
ISBN:
(数字)9783031802362
ISBN:
(纸本)9783031802355;9783031802386
This book introduces an optimal iterative learning control (ILC) design framework from the end user's point of view. Its central theme is the understanding of model dynamics, the construction of a procedure for systematic input updating and their contribution to successful algorithm design. The authors discuss the many applications of ILC in industrial systems, applications such as robotics and mechanical testing.
The text covers a number of optimal ILC design methods, including gradient-based and norm-optimal ILC. Their convergence properties are described and detailed design guidelines, including performance-improvement mechanisms, are presented. Readers are given a clear picture of the nature of ILC and the benefits of the optimization-based approach from the conceptual and mathematical foundations of the problem of algorithm construction to the impact of available parameters in making acceleration of algorithmic convergence possible. Three case studies on robotic platforms, an electro-mechanical machine, and robot-assisted stroke rehabilitation are included to demonstrate the application of these methods in the real-world.
With its emphasis on basic concepts, detailed design guidelines and examples of benefits,
Optimal Iterative Learning control
will be of value to practising engineers and academic researchers alike.
This book constitutes the refereed proceedings of the 12th Annual Conference Towards Autonomous roboticssystems, TAROS 2011, held in sheffield, UK, in August/September 2011.;The 32 revised full papers presented toget...
详细信息
ISBN:
(数字)9783642232329
ISBN:
(纸本)9783642232312
This book constitutes the refereed proceedings of the 12th Annual Conference Towards Autonomous roboticssystems, TAROS 2011, held in sheffield, UK, in August/September 2011.;The 32 revised full papers presented together with 29 two-page abstracts were carefully reviewed and selected from 94 submissions. Among the topics addressed are robot navigation, robot learning, human-robot interaction, robot control, mobile robots, reinforcement learning, robot vehicles, swarm robotic systems, etc.
The scope of this book is to present the papers included at the 21st UK Workshop on Computational Intelligence (UKCI 2022), hosted by The University of sheffield, between 7 and 9 September 2022, sheffield, UK. This ma...
详细信息
ISBN:
(数字)9783031555688
ISBN:
(纸本)9783031555671
The scope of this book is to present the papers included at the 21st UK Workshop on Computational Intelligence (UKCI 2022), hosted by The University of sheffield, between 7 and 9 September 2022, sheffield, UK. This marks the first fully in-person UKCI conference, following the pandemic, a testament to the success and resilience of the UKCI community, as well as to the importance of computational intelligence (CI) research. The papers in this book are divided into five sections: fuzzy logic systems, machine learning, hybrid methods and network systems, deep learning and neural networks, and optimization and search.
暂无评论