In industrial processes, soft sensor models are commonly developed to estimate values of quality-relevant variables in real time. order take advantage the correlations between process variables, two convolutional neural network (CNN)-based this work. By making use unique architecture CNN, first model is capable utilizing abundant data, and complexity remains low. The second integrates finite impulse response dynamics can be reasonably embraced model. effectiveness validated by a simulation...

An axle box bearing is one of the most important components high-speed EMUs (electric multiple units), which runs at a very fast speed, suffers heavy load, and operates under various complex working conditions. Once fault occurs, it not only has an enormous impact on railway system, but also poses threat to personal safety. Therefore, there significant value in studying real-time early warning EMU bearing. However, our best knowledge, are three obvious defects existing methods used for...

In this paper, we investigate the adaptive state-feedback stabilization problem for a class of nonlinear systems subject to parametric uncertainties, time-varying delay, and Markovian jumping actuator failures. First, some fundamental results, including infinitesimal generator conditions existence uniqueness solution, are established w.r.t. vector delay. Subsequently, corresponding stability criterion is generalized considered systems. By employing backstepping method tuning function...

The spherical parallel machine has become the world's academic and industrial focus of field in recent years due to its simple economical manufacture as well structural compactness especially suitable for areas where space gesture changes. This paper dwells upon present research development home abroad. newer (RGRR-II) can rotate around axis z within 360° y1 from -90° +90°. It advantages such less moving parts (only 3 parts), larger ratio work size, zero mechanic coupling, no singularity....

In this paper, an adaptive control algorithm within a U-model framework is developed for controlling class of stochastic non-linear discrete-time models with unknown parameters. With the authors' previous justification, control-oriented model not only represents wide range smooth (polynomial) dynamic plants (without using linearisation approximation at all), but also makes almost all linear system design techniques directly applicable to (with root solver bridging and calculation controller...

The promoting international trade makes the container transportation more important than ever. So and researchers are interested in design research of quay crane. A crane consists gantry, trolley, main hoist, luffing gear spreader etc. It is significance to study mechanism for designing manufacturing cranes. This paper analyses transmission hoist crane, builds mathematics models steel wire part from electromotor convolution, data translation So, it possible simulate motion curve a computer...

A data-driven fault tolerant control for singularly perturbed systems is presented in this paper. It founded on the full state observer and Youla controller parameterization. Based multiplex residual generator identification of parity subspace, an extended internal model (EIMC) structure proposed then design parameters given accordingly. Since system disturbed by faults, paper can accurately track parameters. At last a numerical example to illustrate feasibility effectiveness method.

Dimensionless Peclet number is applied to describe the flow behavior in a specially designed wastewater reactor with compound pattern of plug-flow, baffled-flow and mixed-flow. A set numbers obtained for different fluid conditions by measuring residence time distribution tracer reactor. Some experiments were made examine quantitative influence on removal efficiency COD, NH4+-N TP, results shown that there an optimum representing certain at which best rates TP are obtained.

This paper designs a double-loop cascade active disturbance rejection control (ADRC) to overcome the external disturbances and parameter uncertainty during hypersonic vehicle flight. The attitude angle angular velocity are regulated in outer loop inner loop, respectively. A stochastic robust approach is employed further tune ADRC parameters for better performances. Monte Carlo sampling of uncertain adopted evaluate performance. An improved differential evolution algorithm that combines...

This paper firstly establishes a mathematical model of ship power system, and then analyzes the characteristics common faults system. D-S evidence theory method is used on research to enhance pertinence fault diagnosis. By using multi-source information fusion diagnosis, need for quantities electrical data reduced, and, it can effectively reduce impact protection or switch malfunction diagnosis system thus improve accuracy

The problem of reliable control for variable fault systems under linear quadratic Gaussian (LQG) framework is studied in this paper. Firstly, a cluster models used to cover the dynamic behaviors different modes system and, each model, LQG implemented. By using posteriori probability model innovation as weight information, multi-model (MMRC) proposed. Secondly, it proved that MMRC can enable controller learn real operating mode system. When deadlock state, avoidance strategy given and its...

This paper presents a observer-based fault estimation method for class of singularly perturbed systems subjected to parameter uncertainties and time-delay in state disturbance signal with finite energy. To solve the problem involving actuator sensor uncertain disturbed time-delay, we studied is firstly transformed into standard $ H_\infty control problem, which performance index \gamma represents attenuation energy disturbance. By adopting Lyapunov function \varepsilon $-dependence,...

This paper considers a dual control problem for stochastic linear MIMO (Multiple Input Multiple Output) systems with parameter uncertainty. A novel adaptive law is proposed. The design based on the innovation of cost function, which was originally developed conventional systems. However, process modified and to cater case. more challenging because superposition uncertainty property makes intractable. As in all strategies, it leads that balances out need caution, due uncertainty, conflicting...

With the diversification of demand for new construction and reconstruction transmission lines, capacity increasing conductor will be gradually applied to AC/ DC lines various voltage levels. In existing line design, sag are evaluated by empirical formula, which is verified merely in a 60 meters small span test laboratory, quite different from actual project. To understand temperature rise characteristics typical conductors provide basis selection conductor, first 200 m large on strain tower...