A5091246696- Control Systems and Identification
- Fault Detection and Control Systems
- Energy Load and Power Forecasting
- Structural Health Monitoring Techniques
- Metaheuristic Optimization Algorithms Research
- Wind and Air Flow Studies
- Building Energy and Comfort Optimization
- Advanced Algorithms and Applications
- Vehicle Routing Optimization Methods
- High voltage insulation and dielectric phenomena
- High-Voltage Power Transmission Systems
- Advanced Manufacturing and Logistics Optimization
- Industrial Vision Systems and Defect Detection
- Gear and Bearing Dynamics Analysis
- Advanced Control Systems Optimization
- Optimization and Packing Problems
Taizhou University
2019-2024
The existing results show the applicability of Over-Parameterized Model based Hammerstein-Wiener model identification methods. However, it requires to estimate extra parameters and performer a low rank approximation step. Therefore, may give rise unnecessarily high variance in parameter estimates for highly nonlinear systems, especially using small noisy data set. To overcome this corruptive phenomenon. phenomenon, paper, robust method is developed systems when set, where two parsimonious...
<abstract> <p>This study was purposed to design a multimodal continuous optimization algorithm based on scheme agent address the multidimensional complexity of optimization. An evolutionary sampling method subarea exploration and multiple exploitations developed by employing with variable population size so as obtain higher speed accuracy. Second, distribution plan quantified into high-dimensional parameters characteristics logistics problems, discrete model constructed. Then, we...
In this paper, a recursive closed-loop subspace identification method for Hammerstein nonlinear systems is proposed. To reduce the number of unknown parameters to be identified, original hybrid system decomposed as two parsimonious subsystems, with each subsystem being related directly either linear dynamics or static nonlinearity. avoid redundant computations, least-squares (RLS) algorithm established identifying common terms in while another RLS algorithms are estimate coefficients and...
Background The thickness accuracy of strip is an important indicator to measure the quality strip, and control key for high-quality products in rolling industry. Methods A prediction method based on Long Short-Term Memory (LSTM) optimized by improved border collie optimization (IBCO) algorithm proposed. First, chaotic mapping dynamic weighting strategy are introduced into IBCO overcome shortcomings uneven initial population distribution inaccurate states some individuals Border Collie...
Substation equipment temperature is difficult to achieve accurate prediction because of its typical seasonality, periodicity and instability, complex working environment less available characteristic information.To overcome these difficulties, a substation method proposed based on multivariate information fusion, convolutional neural network (CNN) gated recurrent unite (GRU) in this article. Firstly, according the correlation analysis including linear mapping, autocorrelation function...
Temperature prediction of substation equipment is one the important means for intelligent inspection equipment. However, there are still three challenges: (1) Limited extracted samples; (2) Typical nonlinearity, seasonality, and periodicity; (3) Changes in working conditions. To solve problems above, a temperature method considering Spatio-temporal relationship (SETPM-CLSTR) proposed. First, according to time series from two aspects temporal spatial, it determined that has seasonal,...