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.
For the patients with type 1 diabetes (T1D), it is very important to keep their blood glucose concentration in the normal level by insulin injections. As the glucose level can be checked consistently by continuous glucose monitoring (CGM) system, it enables estimation of near-future glucose prediction by developing a reliable prediction model. In this paper, a kernel-based adaptive filtering algorithm...
In this paper, a new method is presented for identification of single-input single-output (SISO) nonlinear systems with long time delay. The proposed dynamic extreme learning machine (DELM) is different from extreme learning machine in that it adds adaptive delay parameters in the output layer of the network, and the delay parameter is optimized by use of particle swarm algorithm. The dynamic extreme...
Kernel partial least squares(KPLS) is widely adopted for soft-sensing in nonlinear industrial process. For KPLS method, the determination of central nodes and kernel width in the kernel function will affects generalization ability and predictiability. This paper proposes an entropy-clustering and K-means based KPLS regression method. First of all, it divides the original data into several clusters...
Both the plant parameter4 and delay time of the system may vary in the time-varying system, which makes system identification relatively complex. In this paper, a new system identification algorithm based on subspace method and cross-correlation function is proposed to identify system parameter and time-delay simultaneously. The time delay is identified with the calculation of the cross-correlation...
For the solution of optimal control problem involving an index-1 differential-algebraic equation, an efficient function evaluation algorithm is proposed in this paper. In the evaluation procedure, the state equation is propagated forwards, then, adjoint sensitivity is propagated backwards. Thus, it is computationally more efficient than forward sensitivity propagation when the number of constraints...
Battery energy storage systems (BESS) are widely used in wind power systems to improve the dispatchability of wind power. In this paper, a wind power trading strategy using controllable BESS is presented to maximize the profit of wind power plants. A dynamic programming algorithm is produced to control the operation of BESS based on forecasted wind power, electricity price and battery lifetime estimation...
Facing the background of active vibration control of large flexible space structures, an active vibration controller with hybrid FxLMS algorithm is analyzed and implemented. The hybrid FxLMS algorithm is the combination of FxLMS algorithm and feedback FxLMS algorithm. It could solve the problem that the reference signal of FxLMS algorithm cannot be separated from the measurement noises and impulsive...
Effective mechanical state prediction systems are critical to modern manufacturing systems and industries. As a method of deep learning algorithm, Recurrent neural network, (RNN) has been playing an increasingly important role in the field of time series prediction. In order to solve the problem of hard training and gradient extinction of RNN model, a long short-term memory network (LSTM) algorithm...
The prediction of PM2.5 is difficult because the variation of PM2.5 concentration is a nonlinear dynamic process. Therefore, a recurrent fuzzy neural network prediction method is proposed to predict the PM2.5 concentration in this paper. Firstly, the partial least squares (PLS) algorithm is used to select key input variables as a preprocessing step. Then, a recurrent fuzzy neural network model is...
To improve the simulation accuracy of disease prediction model, a modified hybrid algorithm combining BP neural network (BPNN) with particle swarm optimization (PSO) algorithm based on chaos theory optimization is proposed considering BPNN is easy to fall into the local extremum. The chaos theory is used to optimize PSO algorithm to overcome the premature convergence of the traditional PSO algorithm...
Aiming at the problem of network security situation prediction, this paper studies the prediction method based on RBF neural network. Through training the RBF neural network, find out the nonlinear mapping relationship between the front N data and the subsequent M data, and then adjust the value of N to explore the different prediction results. The simulation result shows that the proposed method...
This paper investigates the wind speed forecast for the stratospheric airship fixed over a geo-location because the wind speed forecast is a key challenge for the airship station-keeping control. In view of the wind speed series which changes with the time and space and shows the non-linear and non-stationary characteristics, this paper put forward a kind of adaptive model based on Incremental extreme...
In this paper, an algorithm that based on pca-bp-bagging model is developed for the prediction of pathological data. This algorithm aims at improving the characteristics of bp neural network that the prediction accuracy of pathological data is low, the generalization ability of single bp neural network model is poor, and the anti-interference ability is weak. To enhance the performance of the whole...
For multivariable coupling systems with large time delay, a feed-forward decoupling control algorithm is proposed based on the generalized predictive control (GPC). Similar with feed-forward control former, the coupling effect from other control channels is handled as strong disturbance. The related coupling matrix λ and R in GPC algorithm are decomposed and proper parameters are chosen to realize...
In papermaking process, headbox is a key component of the paper machine, whose output has big influences on the produced paper quality and operation safety. In this paper, the double air-cushioned headboxes structure is modelled in a cascaded way, in which we take the liquid level and air-cushioned pressure into consideration. To achieve stable and fast-responded control performance for the proposed...
The inherent characteristics of processes in practice can be more precisely described by the fractional order differential equations because of the arbitrary orders and the distinctive memory feature of fractional order calculus. In this paper, a fractional order PID-type dynamic matrix controller is designed for a class of fractional order linear single input and single output systems. The approximate...
Reference evapotranspiration (ET0) plays an important role in water resources scheduling of irrigation systems. This paper proposes a novel extreme learning machine (ELM) method optimized by particle swarm optimization (PSO) algorithm (PSO-SWELM) to realize more accurate evapotranspiration estimation with limited environmental and meteorological data. The weights and thresholds between input and hidden...
To solve the problem of gradient descent (GD) method which has low accuracy and easily falling into local optimum, the radial basis function (RBF) based on immune algorithm system (IAS-RBF) is proposed. In this method, each antibody is a RBF neural network and the optimal affinity is calculated by immune algorithm system (IAS) to get the best antibody, then the optimal parameter of RBF neural network...
In this paper, the trajectory tracking control problem with model predictive control approach is investigated for Unmanned Underwater Vehicle (UUV) control. Firstly, the kinematic tracking controller based on model predictive control (MPC) is applied to reach the tracking control in a kinematic way. Compared with conventional backstepping control, MPC can solve the speed jump control problem very...
To solve the real-time orbit determination for impulse maneuver satellite, this paper proposes a strong tracking cubature Kalman filter (STCKF) algorithm. This algorithm uses the equivalent representation of strong tracking filter (STF) to calculate suboptimal fading factor so as to real-timely adjust the gain matrix online. In this way, residual error series are forced to be mutually orthogonalized,...
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.