Search

In order to identify time-varying transient modal parameters only from nonstationary vibration response measurement signals for slow linear time-varying (SLTV) structures which are weakly damped, a moving window differential evolution (DE) independent component analysis- (ICA-) based operational modal analysis (OMA) method is proposed in this paper. Firstly, in order to overcome the problems in traditional ICA-based OMA, such as easy to go into local optima and difficult-to-identify high-order modal parameters, we combine DE with ICA and propose a differential evolution independent component analysis- (DEICA-) based OMA method for linear time invariant (LTI) structures. Secondly, we combine the moving widow technique with DEICA and propose a moving window differential evolution independent component analysis- (MWDEICA-) based OMA method for SLTV structures. The MWDEICA-based OMA method has high global searching ability, robustness, and complexity of time and space. The modal identification results in a three-degree-of-freedom structure with slow time-varying mass show that this MWDEICA-based OMA method can identify transient time-varying modal parameters effectively only from nonstationary vibration response measurement signals and has better performances than moving window traditional ICA-based OMA.

Digital image noise may be introduced during acquisition, transmission, or processing and affects readability and image processing effectiveness. The accuracy of established image processing techniques, such as segmentation, recognition, and edge detection, is adversely impacted by noise. There exists an extensive body of work which focuses on circumventing such issues through digital image enhancement and noise reduction, but this work is limited by a number of constraints including the application of non-adaptive parameters, potential loss of edge detail information, and (with supervised approaches) a requirement for clean, labeled, training data. This paper, developed on the principle of Noise2Void, presents a new unsupervised learning approach incorporating a pseudo-siamese network. Our method enables image denoising without the need for clean images or paired noise images, instead requiring only noise images. Two independent branches of the network utilize different filling strategies, namely zero filling and adjacent pixel filling. Then, the network employs a loss function to improve the similarity of the results in the two branches. We also modify the Efficient Channel Attention module to extract more diverse features and improve performance on the basis of global average pooling. Experimental results show that compared with traditional methods, the pseudo-siamese network has a greater improvement on the ADNI dataset in terms of quantitative and qualitative evaluation. Our method therefore has practical utility in cases where clean images are difficult to obtain.

Diabetic retinopathy (DR) is an eye abnormality caused by chronic diabetes that affected patients worldwide. Hard exudate is an important and observable sign of DR and can be used for early diagnosis. In this paper, an automatic hard exudates segmentation method is proposed in order to aid ophthalmologists to diagnose DR in the early stage. We utilized the SLIC superpixel algorithm to generate sample patches, thus overcoming the difficulty of the limited and imbalanced dataset. Furthermore, a U-net based network architecture with inception modules and residual connections is proposed to conduct end-to-end hard exudate segmentation, and focal loss is utilized as the loss function. Extensive experiments have been conducted on the IDRiD dataset to evaluate the performance of the proposed method. The reported sensitivity, specificity, and accuracy achieve 96.38%, 97.14%, and 97.95% respectively, which demonstrates the effectiveness and superiority of our method. The achieved segmentation results prove the potential of the method for clinical diagnosis.

This paper introduces the exergy efficiency that takes into account both the quantity and quality of energy, and constructs a bi-level planning optimization model of the regional integrated energy system. Factors such as equipment exergy efficiency are considered by the upper-level planning model. Through matter-element information theory and Frequent Patterm-growth algorithm, the energy structure of the regional integrated energy system planning is determined by quantitative means. The lower-level planning model is intended for economy and exergy efficiency, and the tabu search algorithm is embedded in the solving algorithm of the multi-objective genetic algorithm for solving, determining the capacity of each equipment in the energy structure. In the case study, three comparison schemes are used to verify the proposed model and method through the regional integrated energy system in a resort town in northern China. Among them, Scheme 1 is devised for economy, Scheme 2 is proposed for economy and energy efficiency, and Scheme 3 is intended for economy and exergy efficiency. The results show that compared with the Scheme 1 and Scheme 2, the system exergy efficiency of Scheme 3 corresponding to this model has increased by 17.34% and 11.17%, respectively. Despite an increase of 10.61% in total annualized cost in Scheme 3 compared to Scheme 1, there is a decrease of 6.37% compared to Scheme 2. Despite the conflict in improving exergy efficiency and economy, there is still a balance to draw in the proposed model in this paper.

In this paper, we propose a new semantic segmentation network called ’E-Res U-Net’, to achieve better segmentation results of deep and superficial muscles in ultrasonic muscle images. This model is based on U-Net, and its structure has been modified to improve the performance of the algorithm. There are three aspects of improvement based on U-Net, including E-Res layer, dilated convolution module, and E-Res path. Additional experiments demonstrate that each designed module in our proposed network is effective, can improve the accuracy compared to the original U-Net. When compared with other algorithms which are state-of-the-art, the experimental result under the overall network structure is even more excellent.

Direct Current grid technology based on flexible Direct Current transmission is one of the key means to solve large-scale grid integration and consumption of new energy. The flexible Direct Current transmission technology developed in recent years has superior control performance, strong flexibility, and independent control of active power. And reactive power, can be connected to the weak Alternating Current system. This article derives the power flow equation of the Direct Current transmission network by establishing a mathematical model of the Direct Current transmission network and combining different system-level control strategies in the Direct Current transmission network. The Newton-Raphson method is used to solve the power flow distribution of the Direct Current network when the master-slave control and droop control are adopted. The influence of the two control methods on the power flow distribution of the Direct Current network is compared through a calculation example.

This paper proposes a comprehensive energy expansion planning method based on multi-energy coupling, and establishes a mixed integer linear programming model with the goal of minimizing the sum of investment, operation, power shortage, and wind curtailment costs. The model can be used on the basis of ensuring computational efficiency. In the above, the uncertainty of wind power is accurately explored, and a two-stage planning and solving strategy based on the scenario method is established to ensure the efficiency and feasibility of the model solution. GAMS is used to optimize the calculation of the IEEE14-NGS14 example system, and the result of the optimal expansion plan proves the correctness and effectiveness of the method proposed in this paper.

The economy of the Regional Integrated Energy System (RIES) scheduling scheme is affected by the parameter accuracy of different energy conversion equipment models. The traditional static energy hub (EH) model regards the equipment efficiency as a constant and ignores the variable condition characteristics of the equipment efficiency changing with the load rate. This paper presents an optimal scheduling method of RIES considering the characteristics of equipment under variable operating conditions. Firstly, the architecture of the integrated energy system is analyzed. Secondly, based on the DEH model, an optimal scheduling method of RIES was proposed considering the characteristics of equipment under variable operating conditions. Finally, an optimal scheduling analysis is performed for a typical RIs. The results show that the proposed method can improve the accuracy of the equipment model and reduce the cost prediction error by considering the variable operating conditions of the equipment, thus providing a more economical scheduling scheme for Ries.

This paper studies the design of clean electric energy alternatives based on electric energy alternative equipment. First, sort out the current research status of energy substitution at home and abroad, and determine the research focus of electric energy substitution; list the electric energy substitution equipment that is suitable for construction, industrial, commercial and other fields, analyze its technical characteristics and specific application scenarios; list each device To analyze the performance of the equipment, establish a multi-factor output model for energy storage and production equipment according to the key influencing factors of the equipment performance coefficient; finally, based the above research, consider the substitutability of each equipment With complementary characteristics, the design is suitable for high-clean energy electric energy to replace typical structures.

Traditional demand response technologies optimize the load profile by cutting or shifting the electrical load, but they affect the customer’s energy experience, and thus the customer’s motivation to participate in demand response and load controllability are limited. For community integrated energy operators, the study of integrated customer demand response can explore their dispatch potential. Based on consumer psychology, we study the alternative energy use behavior of residential customers, establish a customer optimization model and a community integrated energy operator optimization model, and set up a Stackelberg master-slave game model with the operator as the leader and the customer as the follower. The simulation case verifies that the utilization of load-side multi-energy complementary characteristics and integrated demand response behavior can effectively improve the utilization of renewable energy and the efficiency of integrated energy operators.

With the development of renewable energy technology, integrating a variety of renewable energy integrated energy systems can effectively solve the problem of optimizing the scheduling of buildings with high energy consumption and fast growth rate. Based on the modeling and analysis of various energy equipment in the system, the integrated energy system of building buildings, based on the demand response compensation price, with the lowest construction operating cost as the goal function, establishes the optimization scheduling model of building-level integrated energy system based on demand response, and uses the particle group algorithm based on cloud model improvement to optimize the solution of the model. The study is introduced for simulation to compare the two different modes of participation in demand response, and the optimal performance of cloud model particle group algorithm and elementary particle group algorithm. The results show that the cloud model particle group algorithm model based on demand response can effectively save the operating cost of the building-level integrated energy system, and reduce the power grid side load peak and valley difference.

Due to the limitations of a single power load forecasting model, the power load forecasting cannot be performed well. In order to obtain a greater closeness to predict results with actual data, this paper presents the power load forecasting model based on gray neural network combined return to Guangzhou, 2010 - 2019 on actual data for example, the results show that: As used herein, the combined model method has high accuracy and strong use value.