This paper presents a new method for the correct selection of mining methods and pre-diction of main technological and economic indexes of the face in the gentle inclined thick seams with the application of the artifi...This paper presents a new method for the correct selection of mining methods and pre-diction of main technological and economic indexes of the face in the gentle inclined thick seams with the application of the artificial neural network theory and the expert system. The theory anal- ysis and calculating results indicate that the method is reliable, practical and precise. This method has strongly capabilities of self-study and non-linear dynamic data process. It is expected to be widely applied in the policy decision and prediction of mining technology in coal mine.展开更多
A new superstructure form of heat exchanger networks (HEN) isproposed based on expert system system (ES). The new superstructureform is combined with the practical engineering. The differentinvestment cost formula for...A new superstructure form of heat exchanger networks (HEN) isproposed based on expert system system (ES). The new superstructureform is combined with the practical engineering. The differentinvestment cost formula for Different heat exchanger is alsopresented based on ES. The mathematical model for the simultaneousoptimization Of network configuration is established and solved by agenetic algorithm. This method can deal with larger scale HENsynthesis and the optimal HEN configuration is obtainedautomatically. Finally, a case study is presented to Demonstrate theeffectiveness of the method.展开更多
In cooperative multiagent systems, to learn the optimal policies of multiagents is very difficult. As the numbers of states and actions increase exponentially with the number of agents, their action policies become mo...In cooperative multiagent systems, to learn the optimal policies of multiagents is very difficult. As the numbers of states and actions increase exponentially with the number of agents, their action policies become more intractable. By learning these value functions, an agent can learn its optimal action policies for a task. If a task can be decomposed into several subtasks and the agents have learned the optimal value functions for each subtask, this knowledge can be helpful for the agents in learning the optimal action policies for the whole task when they are acting simultaneously. When merging the agents’ independently learned optimal value functions, a novel multiagent online reinforcement learning algorithm LU-Q is proposed. By applying a transformation to the individually learned value functions, the constraints on the optimal value functions of each subtask are loosened. In each learning iteration process in algorithm LU-Q, the agents’ joint action set in a state is processed. Some actions of that state are pruned from the available action set according to the defined multiagent value function in LU-Q. As the items of the available action set of each state are reduced gradually in the iteration process of LU-Q, the convergence of the value functions is accelerated. LU-Q’s effectiveness, soundness and convergence are analyzed, and the experimental results show that the learning performance of LU-Q is better than the performance of standard Q learning.展开更多
The expert system (ES) techology is combined with artificial neural network (ANN) theory and engineering experience. Based on the framework of artificial meural network, a BackPropagation is structured. Discuss the us...The expert system (ES) techology is combined with artificial neural network (ANN) theory and engineering experience. Based on the framework of artificial meural network, a BackPropagation is structured. Discuss the use of ANN for non-linear diagnosis of damage of prestressed bolt and prestressed concrete piles (PCP) during driving in rock underground engineering and civil engineering. IN terms of Chinese windows95 utilizes C+ + and AINET and XI-PLUS software, make it a reality.展开更多
This paper considers the fourth stage of development of hierarchical control ofindustrial processes to the intelligent control and optimization stage, and reviews what theauthor and his Group have been investigating f...This paper considers the fourth stage of development of hierarchical control ofindustrial processes to the intelligent control and optimization stage, and reviews what theauthor and his Group have been investigating for the past decade in the on-line steadystate hierarchical intelligent control of large-scale industrial processes (LSIP). This papergives a definition of intelligent control of large-scale systems first, and then reviews the useof neural networks for identification and optimization, the use of expert systems to solvesome kinds of hierarchical multi-objective optimization problems by an intelligent decisionunit (ID), the use of fuzzy logic control, and the use of iterative learning control. Severalimplementation examples are introduced. This paper reviews other main achievements ofthe Group also. Finally this paper gives a perspective of future development.展开更多
文摘This paper presents a new method for the correct selection of mining methods and pre-diction of main technological and economic indexes of the face in the gentle inclined thick seams with the application of the artificial neural network theory and the expert system. The theory anal- ysis and calculating results indicate that the method is reliable, practical and precise. This method has strongly capabilities of self-study and non-linear dynamic data process. It is expected to be widely applied in the policy decision and prediction of mining technology in coal mine.
基金Supported by the Natural Science Foundation of Guangdong Province (No. 990630) and the State Major Basic Research Development Program (G20000263).
文摘A new superstructure form of heat exchanger networks (HEN) isproposed based on expert system system (ES). The new superstructureform is combined with the practical engineering. The differentinvestment cost formula for Different heat exchanger is alsopresented based on ES. The mathematical model for the simultaneousoptimization Of network configuration is established and solved by agenetic algorithm. This method can deal with larger scale HENsynthesis and the optimal HEN configuration is obtainedautomatically. Finally, a case study is presented to Demonstrate theeffectiveness of the method.
文摘In cooperative multiagent systems, to learn the optimal policies of multiagents is very difficult. As the numbers of states and actions increase exponentially with the number of agents, their action policies become more intractable. By learning these value functions, an agent can learn its optimal action policies for a task. If a task can be decomposed into several subtasks and the agents have learned the optimal value functions for each subtask, this knowledge can be helpful for the agents in learning the optimal action policies for the whole task when they are acting simultaneously. When merging the agents’ independently learned optimal value functions, a novel multiagent online reinforcement learning algorithm LU-Q is proposed. By applying a transformation to the individually learned value functions, the constraints on the optimal value functions of each subtask are loosened. In each learning iteration process in algorithm LU-Q, the agents’ joint action set in a state is processed. Some actions of that state are pruned from the available action set according to the defined multiagent value function in LU-Q. As the items of the available action set of each state are reduced gradually in the iteration process of LU-Q, the convergence of the value functions is accelerated. LU-Q’s effectiveness, soundness and convergence are analyzed, and the experimental results show that the learning performance of LU-Q is better than the performance of standard Q learning.
文摘The expert system (ES) techology is combined with artificial neural network (ANN) theory and engineering experience. Based on the framework of artificial meural network, a BackPropagation is structured. Discuss the use of ANN for non-linear diagnosis of damage of prestressed bolt and prestressed concrete piles (PCP) during driving in rock underground engineering and civil engineering. IN terms of Chinese windows95 utilizes C+ + and AINET and XI-PLUS software, make it a reality.
基金This research is supported by the National Science Fund and is supported by the High Technology Plan (863 plan)of P.R.of China
文摘This paper considers the fourth stage of development of hierarchical control ofindustrial processes to the intelligent control and optimization stage, and reviews what theauthor and his Group have been investigating for the past decade in the on-line steadystate hierarchical intelligent control of large-scale industrial processes (LSIP). This papergives a definition of intelligent control of large-scale systems first, and then reviews the useof neural networks for identification and optimization, the use of expert systems to solvesome kinds of hierarchical multi-objective optimization problems by an intelligent decisionunit (ID), the use of fuzzy logic control, and the use of iterative learning control. Severalimplementation examples are introduced. This paper reviews other main achievements ofthe Group also. Finally this paper gives a perspective of future development.
