We propose a new machine learning architecture with integrated system control and resource management capability for use in autonomous sensing applications with limited resources. Novel neural network dimensionality r...
详细信息
We propose a new machine learning architecture with integrated system control and resource management capability for use in autonomous sensing applications with limited resources. Novel neural network dimensionality reduction with a mixture-of-experts classifier ensures that only relevant information is processed while handling missing sensor data. A genetic optimisation algorithm is used to control the system in the presence of dynamic events, while ensuring that system constraints are met. This tight integration of control optimisation and machine learning algorithms results in a highly efficient intelligent sensor network. The applicability of our technology in remote health monitoring and environmentalmonitoring is shown.
Multi-agent system with distributed structure is an important research field in intelligentcontrol and fault diagnosis system. Based on the research of cooperation and coordination function of multi-agent, a systemat...
详细信息
ISBN:
(纸本)0780384032
Multi-agent system with distributed structure is an important research field in intelligentcontrol and fault diagnosis system. Based on the research of cooperation and coordination function of multi-agent, a systematic structure which integrates control, diagnosis and monitoring is established and those models, cooperation strategy, reasoning machine are also designed. This new decentralization system has been successfully used in actual product line, and provides a new way for industrial control problem.
The three-mode proportional-integral-derivative (PID) controller is widely used industrial process due to ease of use and robustness in the face of plant uncertainties. However, it is very difficult to achieve an opti...
详细信息
Many types of motor drivers have been developed to meet various mission requirements for robots, but any of them are sufficient so that, new motor drivers are yet to developed. In this paper, the software of a control...
详细信息
Many types of motor drivers have been developed to meet various mission requirements for robots, but any of them are sufficient so that, new motor drivers are yet to developed. In this paper, the software of a control motor controller called the Netroller is explained, intelligent and distributed motor controller for variable mission requirements. The Netroller drives a motor or any actuator with the pulse width modulation (PWM) mode. The Netroller consists of a microcomputer unit (MPU) and a communication network that interface that can connect the Netroller each other by control area network (CAN) and the Netroller complies reducing harness complexity. The Netroller communicate with a main concentrated computer unit (MCCU). Furthermore the Netroller is very small, so enable to distribute the robot joints. An example is applying the Netroller to the reconfiguration brachiating space robot (RBR) for improving robot performance and reliability.
Automated fault diagnosis becomes increasingly important to satellite work. In an early paper, we introduced system level diagnosis theory into satellite iietwork firstly and presented two-level-node graph, a novel mo...
详细信息
ISBN:
(纸本)0780387481
Automated fault diagnosis becomes increasingly important to satellite work. In an early paper, we introduced system level diagnosis theory into satellite iietwork firstly and presented two-level-node graph, a novel modeling method,. Based on these work, a new test invalidation model under certain fault pattern is presented and a diagnosis algorithni is proposed in this paper. Diagnosis can be divided into two steps, local diagnosis and centralized diagnosis. The former is distributed, which can reduce the diagnosis delay by collecting test results in satellites parallelly. The latter is centralized, which can make use of the regularity of satellite network. The procedure of local diagnosis is described by activity cycle diagram. During diagnosing, little professional knowledge about satellite needs to be involved. An example illustrates the diagnosis algorithm and its effect.
Sensor networks are systems of many small units that work together to monitor a given environment. Endowing such sensor units with mobility can allow them to reactively converge on more interesting portions of their e...
详细信息
Sensor networks are systems of many small units that work together to monitor a given environment. Endowing such sensor units with mobility can allow them to reactively converge on more interesting portions of their environment. This enables the concentration of sensing resources where they are most useful and provides robustness by delivering redundancy at the point of interest. However, when converging, in general the sensors should not leave any portion of the environment unsensed. In this paper, we review distributed methods for controlling the sensors and describe a family of distributed methods for retaining coverage while allowing the convergence to proceed where possible. The coverage methods are based on the Voronoi diagram of the sensors' positions, and can use different amounts of communication and computation to produce complete coverage of the environment. We also describe extensions that serve to make coverage more uniform or allow specific areas to be left uncovered. We present implementations of these algorithms in simulation and describe results and avenues of future work.
The tendency toward the use of distributed systems is due to these systems have demonstrated to be a good option for the industrial control systems implementation, because of their flexibility and power, which can be ...
详细信息
The tendency toward the use of distributed systems is due to these systems have demonstrated to be a good option for the industrial control systems implementation, because of their flexibility and power, which can be increased with the application of artificial intelligence techniques. In this line, our research group has developed several distributed systems applied to chemical analysis and industrial automation. For these implementations the CAN network was used. Nowadays there is a market for technical tasks like distributedcontrol, monitoring or data acquisition where there is a need for wireless connectivity. Thus, in this paper we want to discuss possibilities and necessary developments to set up wireless communication for industrial applications. Also, an abstract definition of a new layered architecture for the implementation of intelligent and distributed systems interconnected by means of wireless networks is proposed. Several techniques of discrete control may be used, from Petri nets to an expert system based on rule nets, while continuous control loops may be implemented by means of from traditional PID devices to distributed neural network approaches. Finally, for the communication layer implementation, a wireless network such as Bluetooth or ZigBee could be used.
Rolling element bearings are widely used components in industrial equipments and their failure may result in severe damage of critical processes. Bearing plants are required to provide estimated performance data to th...
详细信息
Rolling element bearings are widely used components in industrial equipments and their failure may result in severe damage of critical processes. Bearing plants are required to provide estimated performance data to their customers. These statistically based data are usually got through various testing experiments with product samples via bearing test rig. However, it is usually hard to get convincible results from traditional method due to the limitation of monitoring device and analysis methods. This paper designs an intelligent system for a bearing testing and inspection center of a bearing plant to monitor the health status and assess the performance of bearings being tested. The system has a distributed infrastructure and can continually collect testing data, analyze vibration signals, extract features of bearing fault, diagnose bearing faults and further assess the quality of the bearings. Fuzzy logic, wavelet neural network and dynamic wavelet neural network are employed as diagnostic/prognostic algorithm.
Network Centric Information Infrastructure (NCII) is a toolkit of prefabricated software components together with a composition framework for integration and experimentation. Typical distributed system applications of...
详细信息
Network Centric Information Infrastructure (NCII) is a toolkit of prefabricated software components together with a composition framework for integration and experimentation. Typical distributed system applications of a toolkit such as NCH can be applied to air traffic management, shop floor control and in-flight connection to Internet. The composition framework has gone though through three generations of changes in the past five years and it is a good illustration of a paradigm shift from object-oriented architecture, through component-based architecture to service-based architecture.
The sensor network for monitoringdistributed spatial phenomena has emerged as an area of significant practical interest. In this paper we investigate fundamental issues in detection of spatially distributed phenomena...
详细信息
The sensor network for monitoringdistributed spatial phenomena has emerged as an area of significant practical interest. In this paper we investigate fundamental issues in detection of spatially distributed phenomena under communication constraints. The novelty of the paper is in providing a tradeoff between global performance and costs involved in communication. In particular we focus our attention on boundary estimation and develop a framework to optimize communication costs subject to worst-case misclassification guarantees. It is shown that the communication cost is primarily a function of two parameters: (1) length of the boundary; (2) overall misclassification error - which leads us to the conclusion that wireless sensor network performance is comparable to that obtained with a wired network of sensors.
暂无评论