The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Piezoelectric ceramic micro-positioning platform has been widely used in micro-positioning, vibration control, and manufacturing applications as a core component of precision manufacturing equipment. However, the main drawback of the piezoelectric ceramic micro-positioning platform is the inherent hysteresis nonlinearity, which affects the positioning accuracy because of its non-memoryless as well...
Greenhouse climate is difficult to model as a complex nonlinear system. The solution to the problem of describing the relation between inputs and outputs is using T-S fuzzy modeling which could transform a nonlinear system into several linear systems. During the transition, c-means clustering is used to cluster the variable of inputs and outputs. The result of clustering determines the compose of...
This Paper carried out three phase and single phase short circuit tests and verified the security and stability of large scale wind farms integration on Rongcheng power station. Including location and type of short circuit, system operation conditions and measurement of date, summarized the main work between the wind farms short circuit test. Following the ideas of “unit level-wire level-wind farm...
In order to improve the accuracy and stability of industrial fault detection and diagnosis, this paper introduces the deep learning theory and proposes an improved Deep Belief Networks (DBNs). In the first, this paper introduces the “centering trick” in the pre-training process of network. This method is done by subtracting offset values from visible and hidden variables. Then, in the process of network...
The vehicle monitoring systems are consisted with more than one server. This involves problem of the information sharing and message transmission among the servers. Communication service system is mainly responsible for the problem of how to transfer and analysis of information. This paper puts forward a kind of optimization design method of communication service system for vehicle remote monitoring...
Event-driven controller is designed in this paper on the context of networked communication links. For reducing the network burden, an event generator is employed to reduce the transmitted data in network. Meanwhile, data losses on both sides of the controller are taken into account and captured by random distributions. Considering the time-varying network environment, the probability of the random...
State-of-charge (SOC) estimation methods based on battery model rely heavily on the accuracy of model parameters. And these parameters could vary with environment and the types of batteries. Online battery modeling methods can improve the robustness of SOC estimation algorithms through updating model constantly with real-time data. These methods have far more profound significance on algorithm adaptability...
Image segmentation has always been an important research direction in the field of images processing, however, due to the long cycle of algorithm, the image segmentation techniques have never been widely applied. According to the problem above, a image segmentation algorithm of Gaussian Mixture Model (GMM) based on Map/Reduce is proposed to improve the real-time performance. Firstly, the architecture...
To construction effective simulation meta-models for complex physical simulation system, the “curse of dimension” and the “uncertain and imprecise information” problems have to be addressed firstly. Although simulation meta-models based on neural networks can obtain well performance, the fuzzy inference mechanism of domain expert for practical application problems cannot be simulated. Thus, some prediction...
Bayesian optimization has been demonstrated as an effective methodology for the global optimization. However, it suffers from a computational bottleneck that the inference time grows cubically with the number of observations. In this paper, a Bayesian optimization based on the data-parallel approach is proposed to alleviate this problem. Firstly, an improved geometry motivated clustering algorithm...
The aim of this work is to explore the relationship between the chemical constituents of Yinhuang Granules (YHG) and in vitro antibacterial activity of serum. In this article, 100 batches of YHG samples were collected, and the fingerprints of chemical constituents and antibacterial activity values were determined. Furthermore, a model that characterizes the relationship between the fingerprints and...
In this paper, we consider an optimal parameter and state estimation problem arising in an one-dimensional (1D) magnetohydrodynamic (MHD) flow system, whose dynamics can be modeled by a coupled partial differential equations (PDEs). In this model, the coefficients of the Reynolds number and initial conditions as well as state variables are supposed to be unknown and need to be estimated. An adjoint-based...
In this study, a deep denoising recurrent temporal restricted Boltzmann machine network is proposed for long-term prediction of time series. The network is a deep dynamic network model which is stacked by multiple denoising recurrent temporal restricted Boltzmann machines with strong modeling ability for complex high noise time series data. To better deal with high noise data, a random noise is added...
As solid oxide fuel cell (SOFC) systems fueled with natural gas and biogas are applied widely, the capture and utilization of CO2 in SOFC exhaust gas are important issues. This paper proposes a new SOFC system combined with a solid oxide electrolysis cell (SOEC) stack, which absorbs renewable electrical power such as solar power and wind power to convert CO2 in SOFC exhaust gas into fuel by electrolysis...
Boiler drum system plays a crucial role in the process of chemical industry. It is a complicated dynamic system with both unknown external disturbances and time varying parameters in model. Due to the external and internal disturbances in the process, it is hard to keep system totally stable in the real operating condition. In this paper, time varying parameters in model are identified and the internal...
PLS is widely used in the quality control process system, but it has poor capability in some strong local nonlinear system for fault diagnosis. To enhance the monitoring ability of such type fault, a novel statistical model based on global plus local projection to latent structures (GPLPLS) is proposed. Firstly, the characteristics and nature of quality-related global and local partial least squares...
Researchers have presented some methodologies of decision support for the different stages of disaster operations management (DOM). However, all these methodologies can't address the core issue of how to make the detail emergency response plan. To improve the standardization and automation of disaster operation management, a new method of emergency management based on the activity network technology...
Aiming at the complicated mechanism of the sintering process of the roller kiln and the large delay in the temperature change of the kiln, which brings difficulties to the precise temperature control. This paper presents the integrated model of roller kiln temperature prediction combined with the fusion mechanism and data model. Firstly, based on the analysis of the heat transfer mechanism in the...
Development of precise active traffic control strategies urgently requires real-time estimation for operational metrics in transportation systems satisfying the level of smaller spatial granularity simultaneously. This paper proposed a probability approach to estimate real-time lane-based queue length using license plate recognition (LPR) data. The method first developed a nested logit model to depict...
To remove redundant variables and resolve the high correlation problem of soft sensor modelling, this paper proposed an efficient mutual information(MI) based partial least squares(PLS) method. First, we use MI criterion to sort the variables in a descending order according to their importance. Then the linearity between process variables and quality variables is tested through F test. If there is...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.