In this paper, a multivariate fault prognosis approach based on statistical process monitoring (SPM) methods and time series prediction for turbine machine was proposed. A principal component analysis (PCA) model ...
详细信息
In this paper, a multivariate fault prognosis approach based on statistical process monitoring (SPM) methods and time series prediction for turbine machine was proposed. A principal component analysis (PCA) model using sample data under normal state was built Firstly, fault is detected by squared prediction error (SPE) index, then predicted by AR model. With development of fault process, the SPE will produce a corresponding change and carry important fault information , so calculate statistics of SPE can be characterized and predict the trend of fault and level. A case study on the huge stack gas turbine shows the efficiency of the proposed approach.
Knowledge manufacturing system has the ability of modifying dynamically manufacturing mode rapidly when production environment factors change. It is essential to evaluate the matching degree of established manufacturi...
详细信息
ISBN:
(纸本)9781424494408
Knowledge manufacturing system has the ability of modifying dynamically manufacturing mode rapidly when production environment factors change. It is essential to evaluate the matching degree of established manufacturing mode and changed production environment factors. In this paper, a matching decision model for self-adaptability of knowledge manufacturing system based on the fuzzy neural network is proposed. The changed production environment factors are regarded as linguistic variable inputs. A modified momentum factor B-P algorithm consisting of information feed-forward process and the error back-propagation process is used. The proposed FNN model is employed to evaluate the matching degree of a car-lamp production manufacturing mode to variable environment units. Matching result indicates adaptive degree of manufacturing system. Experiment result demonstrates the method is effective.
In order to solve the problem that the coverage area of ZigBee tree network is restricted by the depth, so that new nodes can not join the network and become a orphan, this paper introduces a project of expanding netw...
详细信息
In order to solve the problem that the coverage area of ZigBee tree network is restricted by the depth, so that new nodes can not join the network and become a orphan, this paper introduces a project of expanding network coverage area. In this project, through the manual of the button, we can choose a qualified end device to convert to the router configuration, then the device as a router receives new nodes to join the network, The requirement would be realized by improving and innovating ZigBee protocol stack. The project works well in the experiment, it saves the device energy and expands the scope of network.
Components of power systems are essentially a special class of nonlinear differential-algebraic equations subsystems, whose index is one and interconnection is local measurable. In this paper, the invertibility of pow...
详细信息
Components of power systems are essentially a special class of nonlinear differential-algebraic equations subsystems, whose index is one and interconnection is local measurable. In this paper, the invertibility of power systems components is discussed. Firstly, the definition of invertibility is presented. Secondly, a recursive algorithm is proposed to judge whether the controlled components are invertable. Then a physically feasible right inverse controller is constructed with which the controlled components are made linearization and decoupled. Finally, an excitation controller is designed for one synchronous generator within multi-machine power systems based on the proposed method in this paper.
In this paper, genetic algorithm and modified dynamic programming are applied to path planning of robotic fish for the first time. Using grid method to the environment modeling and applying genetic algorithm to the pa...
详细信息
In this paper, genetic algorithm and modified dynamic programming are applied to path planning of robotic fish for the first time. Using grid method to the environment modeling and applying genetic algorithm to the path planning, an optimal or sub-optimal robot path can be obtained. Since the robotic fish can't track linear motion, the robot path can be seen as several circular arc. Based on the optimal path obtained via genetic algorithm, modified dynamic programming algorithm is proposed to calculate the shortest circular arc path, fish velocity and direction in every step. Finally the experiment on the robotic fish control software shows the effectiveness of the proposed method.
Solar photovoltaic power generation is a way to utilize the solar energy. Power station monitoring system is ought to be established to maintain the safe and reliable operation of the photovoltaic system and to detect...
详细信息
Solar photovoltaic power generation is a way to utilize the solar energy. Power station monitoring system is ought to be established to maintain the safe and reliable operation of the photovoltaic system and to detect and solve the malfunctions promptly. The monitoring data of the photovoltaic power monitoring system is composed of environmental data, the related data of photovoltaic battery array and relevant data of inverter. The collection, preprocessing and wireless transmission of data are done by ZigBee, the wireless sensor network. The wireless network panel point of ZigBee is divided into FFD (Full Function Device) and RFD (Reduced Function Device), each of which has its own functions. It can conveniently collect surrounding environment information and status data of photovoltaic power on unattended conditions by ZigBee.
This paper researches the consensus problem of high-order multi-agent systems. A new dynamic neighbor-based protocol is proposed which contains two parts, one is the local feedback and the other is the distributed fee...
详细信息
A neural based PID feedback control method for networked process control systems is presented. As there are some uncertain factors such as external disturbance, randomly delayed measurements or control demands in real...
详细信息
A neural based PID feedback control method for networked process control systems is presented. As there are some uncertain factors such as external disturbance, randomly delayed measurements or control demands in real networked process control systems, the proposed PID controller is implemented by backpropagation neural networks whose weights are updated via minimizing tracking error entropy of closed loop systems. To demonstrate the potential applications of the proposed strategy, an example of a simulated batch reactor is provided. The proposed design method is shown to be useful and effective in dealing with network process control systems.
Pulse laser range detector is to measure the distance by estimating the time delay between the emitting pulse and echo *** this paper,a mathematical model for the target echo signal of laser fuze has been established;...
详细信息
Pulse laser range detector is to measure the distance by estimating the time delay between the emitting pulse and echo *** this paper,a mathematical model for the target echo signal of laser fuze has been established;in accordance with this model,the formulas for echo time-delay estimation and for amplitude estimation based on least squares criterion have been *** is argued and simulated that the resolution of echo time-delay estimation could be improved through multi-reference correlation *** illustrate that the approach enables pulsed laser fuze to perform high-precision ranging under a low signal-to-noise ratio condition.
Components of power systems are essentially a special class of nonlinear differential-algebraic equations subsystems, whose index is one and interconnection is local measurable. In this paper, the invertibility of pow...
详细信息
暂无评论