Against the backdrop of global energy transition and climate change, enhancing the grid integration efficiency and quality of renewable energy sources is pivotal for achieving sustainable development goals. This paper introduces a three-phase current source type 5-level grid-connected inverter and its control method, designed to offer a system with adjustable power factor for high-quality stable grid operation. This system is particularly suitable for grid integration of renewable energy generation, effectively suppressing the resonance of the CL filter and reducing harmonic distortion in grid current. Detailed simulations of the system demonstrate that the design maintains exceptional performance under various conditions, particularly showing outstanding adaptability and stability in response to grid voltage fluctuations and load changes.

This paper proposes a NARX network-based modeling method to improve the real-time performance of dynamic component-level engine models. This method combines the component-level model with the NARX network black-box modeling technique. It collects training data by solving the common working equation of the component-level model (N-R model) using the Newton–Raphson method and uses a multilayer feedforward neural network to approximate the nonlinear mapping from the input state space to the solution of the common working equation. This approach eliminates the need for iterative computations in solving the common working equation, thus enhancing the real-time performance of the component-level model. Using the N-R model as the benchmark, simulation results show that the NARX network model with embedded component-level modeling has a maximum dynamic error of 0.061% during ground state modeling and 0.36% across the full envelope; the average runtime for full envelope modeling is 0.046 seconds, which is only 4.3% of that of the benchmark model; for step inputs, the component residual during the dynamic process is only 0.02% of that of the benchmark model. These findings demonstrate that the engine model established by this method has high accuracy, good real-time performance, and robustness.

The control schedule of model predictive control (MPC), which is based on the bounded real lemma and the vertex property, is presented using linear matrix inequality method. Furthermore, the stability of a polytopic controller with linear parameter varying (LPV) model properties is proven. The method can lessen calculative burden and improve the accuracy in traditional MPC, thus the quickness of key point on the MPC can be solved when applied in aircraft engine with strong nonlinearity. Simulation results on reliable turbofan model are shown that the stability and effectiveness of the polytopic MPC method can be guaranteed, and particularly in large transient, the performance of the polytopic MPC method is superior to the traditional PI one.

3D modeling of the Earth's surface is an important topic and finds its various applications in the remote sensing communities. Due to the imaging complexity of optical remote sensing images, the process of creating a digital surface model of the Earth from multi-view optical remote sensing images is both time-consuming and challenging, especially when dealing with large areas. In this work, we propose a deep learning-based approach, called RS-MVSNet, for inferring a digital surface model from multi-view optical remote sensing images. In order to extend state-of-the-art learning-based multi-view stereo techniques to optical remote sensing images, a differentiable affine warping is designed for the first time, which utilizes an affine to Euclidean upgraded camera model to model the mapping relationship between small-sized remote sensing image tiles and their corresponding 3D local scenes in Euclidean space. Based on the differentiable affine warping, RS-MVSNet is abstracted from the complexities associated with remote sensing imaging and inherits generic components for deep learning based multi-view stereo, including multi-scale deep feature extraction, pyramid cost volume construction, regularization and regression. Moreover, an affine epipolar guided feature aggregation module is constructed in the proposed RS-MVSNet framework to accurately aggregate high-resolution remote sensing image features along affine epipolar lines into a finite cost volume. Extensive experiments are conducted on two public datasets, namely MVS3DM and US3D datasets, and our proposed RS-MVSNet shows promising results in terms of accuracy and efficiency.

Exact inference for large, directed graphical models, also known as Bayesian networks (BNs), can be intractable as the space complexity grows exponentially in the tree‐width of the model. Approximate inference, such as generalized belief propagation (GBP), is used instead. GBP treats inference as the Bethe/Kikuchi energy function optimization problem. The solution is found using iterative message passing, which is inefficient and convergent problematic. Recent progress on amortized technique for GBP is an attractive alternative solution that can optimize the Bethe/Kikuchi energy function using (deep) neural networks, requiring no message passing. Despite being efficient, the amortized technique for GBP is applied to undirected graphical models with specific structures and factors, with no guarantee of the approximation quality. This is because the energy function to be amortized is defined by a region (or factor) graph that is ad hoc and difficult to construct to ensure sensible approximations. This paper proposes a new amortized GBP algorithm applied to BN for efficient inference. The proposed algorithm is composed of the following: (i) a new pairwise conversion (PWC) algorithm that converts all the conditional probability distributions in the BN into pairwise factors to facilitate efficient region graph constructions; (ii) following PWC, an improved loop structured region graph (LSRG) algorithm was derived to generate a valid region graph satisfying desired regional properties; and (iii) the energy function defined by the proposed PWC‐LSRG region graph can be directly amortized using (deep) neural networks to ensure sensible approximations. Empirical studies show that the proposed amortized PWC‐LSRG algorithm is of practical use and significantly improves convergence and efficiency compared to conventional algorithms.

Feature selection (FS), which aims to identify the most informative subset of input features, is an important approach to dimensionality reduction. In this article, a novel FS framework is proposed for both unsupervised and semisupervised scenarios. To make efficient use of data distribution to evaluate features, the framework combines data structure learning (as referred to as data distribution modeling) and FS in a unified formulation such that the data structure learning improves the results of FS and vice versa. Moreover, two types of data structures, namely the soft and hard data structures, are learned and used in the proposed FS framework. The soft data structure refers to the pairwise weights among data samples, and the hard data structure refers to the estimated labels obtained from clustering or semisupervised classification. Both of these data structures are naturally formulated as regularization terms in the proposed framework. In the optimization process, the soft and hard data structures are learned from data represented by the selected features, and then, the most informative features are reselected by referring to the data structures. In this way, the framework uses the interactions between data structure learning and FS to select the most discriminative and informative features. Following the proposed framework, a new semisupervised FS (SSFS) method is derived and studied in depth. Experiments on real-world data sets demonstrate the effectiveness of the proposed method.

This paper investigates classification by dictionary learning. A novel unified framework termed self-taught semisupervised dictionary learning with nonnegative constraint is proposed for simultaneously optimizing the components of a dictionary and a graph Laplacian. Specifically, an atom graph Laplacian regularization is built by using sparse coefficients to effectively capture the underlying manifold structure. It is more robust to noisy samples and outliers because atoms are more concise and representative than training samples. A nonnegative constraint imposed on the sparse coefficients guarantees that each sample is in the middle of its related atoms. In this way, the dependency between samples and atoms is made explicit. Furthermore, a self-taught mechanism is introduced to effectively feed back the manifold structure induced by atom graph Laplacian regularization and the supervised information hidden in unlabeled samples in order to learn a better dictionary. An efficient algorithm, combining a block coordinate descent method with the alternating direction method of multipliers, is derived to optimize the unified framework. Experimental results on several benchmark datasets show the effectiveness of the proposed model.

In this paper, we propose a novel unified optimization framework for semi-supervised dictionary learning, which optimizes a graph Laplacian component and the dictionary simultaneously. In the framework, the graph Laplacian is defined on the atoms and the corresponding sparse codings. Since the atoms are more concise and representative than the original training samples, the constructed graph Laplacian can not only effectively capture the manifold structure of training samples, but also be more robust to noise and outliers. Moreover, the dictionary and the graph Laplacian can facilitate each other during the learning iterations. We derive an efficient algorithm by combining the block coordinate descent method with the alternating direction method of multipliers to solve the unified optimization problem. Extensive experimental evaluation on several challenging datasets demonstrates the superior performance of the proposed method.

Graph based Semi-Supervised Learning (G-SSL) methods usually include the stages of the construction of affinity matrix and the mechanism of inferring unknown labels. However, solving each of the stages individually does not fully exploit the potential relationship between the affinity matrix and the labels of samples. In this paper, we formulate the global self-expressiveness induced affinity and Laplacian Regularized Least Squares (LapRLS) into a single optimization model, called as Self-Taught LapRLS (ST-LapRLS). In the unified model, both the given labels and the estimated labels are used to build a better affinity matrix and to facilitate the LapRLS classifer. The proposed ST-LapRLS classifier is explicit, and can be easily extended to deal with out-of-sample problem. We propose an efficient algorithm which combines the alternating direction method of multiplier and LapRLS to solve the unified optimization problem. Experiments on several Benchmark datasets show the superior performance of our method in classification applications.

Data labeling is a tedious and subjective task that can be time consuming and error-prone; however, most learning algorithms are sensitive to noisy labels. This problem raises the need to develop algorithms that can exploit large amount of unlabeled data and also be robust to noisy label information. In this letter, we propose a novel semi-supervised classification framework that is robust to noisy labels, named self-paced manifold regularization. The proposed framework naturally integrates self-paced learning regime into the manifold regularization framework for selecting labeled training samples in a theoretically sound manner, and utilizes locally linear reconstructions to control the smoothness of the classifier with respect to the manifold structure of data. Finally, the alternative search strategy is adopted for the proposed framework to obtain the classifier. The proposed method can not only suppress the negative effect of noisy initial labels in semi-supervised learning, but also obtain an explicit multiclass classifier for newly coming data points. Experimental results demonstrate the effectiveness of the proposed method.

In this letter, we propose a semi-supervised dimensionality reduction method named Discriminative Sparsity Preserving Projection (DSPP). In order to get the feature mapping$f$which projects the high-dimensional data into a low-dimensional intrinsic space, DSPP attempts to maintain the prior low-dimensional representation constructed by the data points and the known class labels and, meanwhile, considers the complexity of$f$in the ambient space and the smoothness of$f$in preserving the sparse representation of data. On one hand, the DSPP method obtains an explicit nonlinear feature mapping for the out-of-sample extrapolation. On the other hand, the DSPP method has a high discriminative ability which is inherited from the sparse representation of data. Experiment results show the effectiveness of the proposed method.