Monthly runoff time series prediction by variational mode decomposition and support vector machine based on quantum-behaved particle swarm optimization

Fault diagnosis of rotor systems is important to prevent unexpected failures. Recently, deep learning (DL) methods, such as a convolutional neural network (CNN), have been utilized in many research areas, including fault diagnosis. DL has gained significant attention thanks to its ability to efficiently learn proper features from input data. It is possible to learn enriched hierarchical features by making the DL architectures deeper; therefore, many studies have been conducted to stack the neural networks, which are the basic building blocks of DL, deeper. However, it becomes difficult to comprehensively train neural network architectures as they become deeper, due to problems in the flow of gradient information during the training phase. In this paper, a direct connection based CNN (DC-CNN) method is proposed to significantly improve training efficiency and diagnosis performance. DC-CNN connects feature maps of different layers within a CNN to improve the gradient information flow over the layers. These additional connections, however, can increase the number of trainable parameters within the network. To prevent problems that might be caused by an increased number of parameters, dimension reduction modules are also developed. Moreover, to consider the anisotropic characteristics inherent in rotor systems, the vibration images containing both spatial and temporal information are generated and utilized. The effectiveness of DC-CNN is validated using experimental data from a rotor testbed. The experimental results indicate that the proposed method outperforms other conventional approaches with a smaller number of parameters. Also, visualizations of the learned features indicate that the proposed method can learn much more effective and significant features. Furthermore, the proposed method outperforms other approaches under conditions of insufficient or noisy data.

Section: B Compared Methodsmentioning

confidence: 99%

Direct Connection-Based Convolutional Neural Network (DC-CNN) for Fault Diagnosis of Rotor Systems

Kim

Jung

et al. 2020

“…The performance of the SD-DPL is evaluated with those of ELM [28], SVM [29], SRC [1], KSVD [10], LCKSVD [11], FDDL [12], DPL [14], ADDL [15], and LC-PDL [16]. We select four face image databases (the Extend Yale B [30], AR [31], MIT CBCL [32], and CMU PIE [33]), two object image databases (Caltech101 [34] and Caltech256 [35]), and a scene image database (15 scene categories [36]) for evaluation.…”

Section: Experiments and Analysismentioning

confidence: 99%

Structural Constraint and Discriminative Constraint Based Dictionary Pair Learning for Image Classification

Yang¹,

Wang

et al. 2020

The dictionary learning algorithm is an effective image classification algorithm. To tackle with the problems including noise, occlusion, small sample problem, and so on, many discriminative dictionary learning models have been proposed. However, the performance of these algorithms might not be satisfactory, the main reason is that some useful features are not effectively disclosed. For example, the coding coefficients of the samples have row sparsity consistency and the block structure property. Maintaining the inherent features of the samples (e.g. the block structure, local characteristics of atoms) is beneficial to enhance the discriminative ability of the model. In addition, a powerful discriminative constraint is also essential to improve the performance of image classification. In the paper, we propose a new structural constraint and discriminative constraint based dictionary pair learning for image classification. In the model, the L21 norm constraint is applied on the analysis sub-dictionary to ensure the row sparsity consistency of the coding coefficients as much as possible. A new discriminative constraint is designed to enforce the representation matrix to be more discriminative, which can be acquired by minimizing the intra-class scatter and maximizing the inter-class scatter of the samples. Besides, we define a new atomic locality constraint, which forces the atoms to preserve the structure information of the samples. Finally, seven benchmark data sets are selected to evaluate the performance of the proposed method in comparison with popular methods. The experimental results outperform the state-of-the-art methods, which demonstrate the efficacy of the proposed model.

“…Pure QPSO is designed to handle mono-objective optimization problems, and its performance has been investigated in many studies [36]- [38]. This operator was developed to solve MOPs in MOQPSO/D, in which the definitions of the personal best and global best were modified for use with an improved Tchebycheff decomposition.…”

Section: Implementation Of Moqpso/d For Moltgs a Quantum-behavementioning

confidence: 99%

Multiobjective Long-Term Generation Scheduling of Cascade Hydroelectricity System Using a Quantum-Behaved Particle Swarm Optimization Based on Decomposition

Yang

2020

Multiobjective long-term generation scheduling (MOLTGS) plays a vital role in coordinating the contradiction between the generation and reliability of cascade hydroelectricity system (CHS). In this paper, a multiobjective quantum-behaved particle swarm optimization based on decomposition (MOQPSO/D) is presented to solve the MOLTGS problem of maximizing total hydroelectricity generation and firm hydroelectricity output. In MOQPSO/D, the improved logistic map is adopted to initialize the population in the feasible space, where various equality and inequality constraints are handled by a constraint handling method based on conversion and repair strategies. An improved Tchebycheff decomposition with a modified generator of direction vectors, a modified QPSO operator and normal cloud mutation are the key components of MOQPSO/D in addressing the nonlinearity and complexity of MOLTGS. The feasibility and effectiveness of MOQPSO/D are verified first on numerical experiments of benchmark instances and then on real engineering examples of the Three Gorges (TG) and Gezhouba (GZB) plants within three representative years. The results show that MOQPSO/D can not only perform better robustness, convergence and diversity performance than other seven competitors but also output a group of Pareto optimal schemes within a reasonable amount of time. So, this paper provides a new effective alternative to solve the MOLTGS problem of CHS when considering both generation and reliability objectives. INDEX TERMS Cascade hydroelectricity system, multiobjective long-term generation scheduling, quantum-behaved particle swarm optimization, improved Tchebycheff decomposition, normal cloud mutation.