Generative adversarial networks (GANs) coming from the game theory allow machines to learn deep representations without extra training data. By training two adversarial networks, including a generator and a discrimina...
详细信息
Generative adversarial networks (GANs) coming from the game theory allow machines to learn deep representations without extra training data. By training two adversarial networks, including a generator and a discriminator, GANs could get the distribution of the real samples. This capability makes it a prospect learning method in image synthesis, image recognition, image translation etc. In this paper, we survey the state of the art of GANs by categorizing the GANs into four classifications on the basis of GANs' functions and list two application domains: vision computing & natural language processing (NLP) regarding to GANs' applications.
This paper investigates the problem of observer-based output feedback control for networked controlsystems with non-uniform sampling and time-varying transmission delay. The sampling intervals are assumed to vary wit...
详细信息
This paper investigates the problem of observer-based output feedback control for networked controlsystems with non-uniform sampling and time-varying transmission delay. The sampling intervals are assumed to vary within a given interval. The transmission delay belongs to a known interval. A discrete-time model is first established, which contains time-varying delay and norm-bounded uncertainties coming from non-uniform sampling intervals. It is then converted to an interconnection of two subsystems in which the forward channel is delay-free. The scaled small gain theorem is used to derive the stability condition for the closed-loop system. Moreover, the observer-based output feedback controller design method is proposed by utilising a modified cone complementary linearisation algorithm. Finally, numerical examples illustrate the validity and superiority of the proposed method.
In the active distribution network (ADN), the interharmonic distortion level is aggravated due to the growing penetration of distributed generations and wide application of power electronic loads. The interharmonics, ...
详细信息
Speed control mode of a DC motor without knowing the specific parameters of the motor is *** approximate mathematical model of the controlsystem is obtained by the system identification when the output of the system ...
详细信息
ISBN:
(纸本)9781538629185
Speed control mode of a DC motor without knowing the specific parameters of the motor is *** approximate mathematical model of the controlsystem is obtained by the system identification when the output of the system is measured by loading the specific input *** PID control algorithm is adopted and the P,I,and D parameters are obtained by auto *** in the loop(HIL) experiments are carried out on MATLAB and Arduino platform,in which the experimental results demonstrate the feasibility of the proposal.
As the main force of power generation in China, coal-fired power plants have great significance for energy conservation and emission reduction. The oxygen content in flue gases is an important index to reflect the com...
详细信息
As the main force of power generation in China, coal-fired power plants have great significance for energy conservation and emission reduction. The oxygen content in flue gases is an important index to reflect the combustion efficiency of the boiler, and the accurate monitoring is an effective way to improve combustion efficiency. Based on the BP neural network, a soft-sensing model for oxygen content in flue gases is proposed in this paper, this article, taking a boiler combustion system of 600 MW coal-fired power plant unit in Jiaxing, Zhejiang as the research object, through real-time measurement data of DCS system, a flue gases oxygen content model is established, and this model has realized the soft measurement to flue gases oxygen content, the simulation results prove the validity of the soft sensing model. This model has great significance to the monitoring of the oxygen content in flue gases of boiler combustion system and the further study of combustion optimization on this basis.
Network is the core element of many industrial and automation systems. In the future, more attention will be paid to convergent and unified network. Time-critical traffic and non-time-critical traffic need to share co...
Network is the core element of many industrial and automation systems. In the future, more attention will be paid to convergent and unified network. Time-critical traffic and non-time-critical traffic need to share communication channels. The goal of the IEEE TSN task group is to extend the existing Ethernet standard to achieve a degree of certainty that meets the hard-real-time requirements of modern control networks in the industrial automation and automotive industries. Time sensitive network (TSN) is characterized by low jitter, low delay and deterministic transmission. It can transmit critical and non-critical traffic in the same network, which is very suitable for time- critical applications with high requirements on transmission delay. This paper briefly summarizes the key components of TSN, studies the key technologies, and carries out a simple traffic scheduling experiment on the switch based on 802.1Qbv function, and finally analyzes the application of TSN in industrial automation and automobile industry.
State estimation and fault diagnosis are essential topics for dynamic *** Kalman fllter(UKF) has been widely applied in nonlinear *** classical UKF algorithm is built on the premise that process noise and measuremen...
详细信息
ISBN:
(纸本)9781538629185
State estimation and fault diagnosis are essential topics for dynamic *** Kalman fllter(UKF) has been widely applied in nonlinear *** classical UKF algorithm is built on the premise that process noise and measurement noise is *** practical problems,this assumption is not always *** addition,due to the limitation of communication and sensor fault,etc.,data missing or unreliable measurements will happen ***,it is very important to study the state estimation of nonlinear systems with unreliable measurements and correlated *** this paper,an UKF based state estimation algorithm with unreliable observations under correlated noise is presented.A numerical example is given to show the feasibility and effectiveness of the presented algorithm.
This technical note studies a class of distributed nonsmooth convex consensus optimization problem. The cost function is a summation of local cost functions which are convex but nonsmooth. Each of the local cost funct...
详细信息
Brain tumours are masses of abnormal cells that can grow in an uncontrolled way in the brain. There are different types of malignant brain tumours. Gliomas are malignant brain tumours that grow from glial cells and ar...
详细信息
Fault diagnosis and location of distribution network is a difficult problem. With the integration of the distributed generation, the multi-source of the fault current makes the problem more complex. This paper propose...
详细信息
Fault diagnosis and location of distribution network is a difficult problem. With the integration of the distributed generation, the multi-source of the fault current makes the problem more complex. This paper proposes a fault diagnosis method based on synchronized measurement information matrix, which includes two procedures: 1) to detect the occurrence of the fault; 2) to locate the fault section and determine the fault type. Firstly, the local covariance matrix is defined by introducing sliding window based on synchronous phasor information. Then, a local information covariance matrix is constructed by taking each PMU's data as a sample at a certain moment to detect the occurrence of the fault. The fault segment is located and the fault type is determined via improving the local covariance matrix. Finally, a simulation example is used to verify the effectiveness and reliability of the proposed method.
暂无评论