Wyniki wyszukiwania - BazTech

1

Dynamic adjustment neural network-based cooperative control for vehicle platoons with state constraints

Wang Ping, Gao Min, Li Junyu, Zhang Anguo

International Journal of Applied Mathematics and Computer Science

|

2024

|

Vol. 34, no. 2

211--224

EN

This paper addresses the challenge of managing state constraints in vehicle platoons, including maintaining safe distances and aligning velocities, which are key factors that contribute to performance degradation in platoon control. Traditional platoon control strategies, which rely on a constant time-headway policy, often lead to deteriorated performance and even instability, primarily during dynamic traffic conditions involving vehicle acceleration and deceleration. The underlying issue is the inadequacy of these methods to adapt to variable time-delays and to accurately modulate the spacing and speed among vehicles. To address these challenges, we propose a dynamic adjustment neural network (DANN) based cooperative control scheme. The proposed strategy employs neural networks to continuously learn and adjust to time varying conditions, thus enabling precise control of each vehicle’s state within the platoon. By integrating a DANN into the platoon control system, we ensure that both velocity and inter-vehicular spacing adapt in response to real-time traffic dynamics. The efficacy of our proposed control approach is validated using both Lyapunov stability theory and numeric simulation, which confirms substantial gains in stability and velocity tracking of the vehicle platoon.

2

Clogging in vertical flow constructed wetlands : causes for clogging and influence of decontamination

Xu QiaoLing, Wang Li, Wang Ping, Wen XueYuan, Zhang Feng

Ecological Chemistry and Engineering. S

|

2022

|

Vol. 29, nr 1

65--75

EN

With the continuous operation of constructed wetlands, substrate clogging is issue. In order to solve the problem, there is practical significance to understand the causes for clogging in constructed wetlands. Two pilot-scale vertical flow constructed wetlands were established, namely, CW-B and CW-C. By studying the relationship between the accumulation of different substances and the banked-up water area, it was found that the accumulation of non-filter substances and total solids was an important reason for the clogging of the substrate, and the accumulation degree of non-filter inorganic substances was more obvious than that of non-filter organic substances, and the blockage was mainly located in the 10-20 cm layer. In the vertical flow constructed wetland with river sand as the main substrate, water accumulation will occur when the content of total solid and non-filter substances exceeds 67.233 g and 101.228 g per cubic meter of substrate, respectively. Therefore, it is important to pay attention to the substrate particle size matching of 0-20 cm layer to reduce the clogging in the vertical flow constructed wetland. The clogging has little effect on chemical oxygen demand (COD) removal, but great effect on total phosphorus (TP) removal. Compared with the control wetland (CW-C), the biomass content in the CW-B with biochar increased by 334.26 nmol P/g, which can improve the removal efficiency of total nitrogen (TN) and total phosphorus (TP), but also increase the risk of clogging in the vertical flow constructed wetland. Future research should try to combine the anti-blocking research results of biochar constructed wetlands to improve the purification effect, which is of great significance to promote the sustainable development of constructed wetlands.

3

Preparation of α-calcium sulfate hemihydrate from industrial by-product gypsum: a review

Guan Qingjun, Sui Ying, Zhang Fang, Yu Weijian, Bo Yongjie, Wang Ping, Peng Wenqing, Jin Jiao

Physicochemical Problems of Mineral Processing

|

2021

|

Vol. 57, iss. 1

168--181

EN

In recent years, the massive accumulation of industrial by-product gypsum, especially flue gas desulfurization (FGD) gypsum and phosphogypsum (PG), not only encroaches on lands but also causes serious environmental pollution. The preparation of α-calcium sulfate hemihydrate (α-HH) from industrial by-product gypsum is an important way to solve the massive accumulation. α-HH possessing larger, dense and well-grown crystals with fewer cracks and pores has high added value and a wide range of application. Hitherto the preparation methods of α-HH from industrial by-product gypsum mainly include the autoclave process, salt/acid solution process, or alcohol-water solution process. Thereinto, the autoclave process is the only method to realize industrialization. In order to solve the high energy consumption and unfavorable continuous operation of the autoclave process, researchers suggested alternative approaches, such as salt/acid solution process and alcohol-water solution process. However, these methods are basically in the laboratory stage or pilot scale test at present. Compared with FGD gypsum, the utilization rate of PG with a larger emission is very low owing to the high impurity content. And combining the preparation of α-HH with the recovery of valuable impurities from PG seems a promising way to solve the bulk deposition of PG.

4

Optical coherence tomography image for automatic classification of diabetic macular edema

Wang Ping, Li Jia-Li, Ding Hao

Optica Applicata

|

2020

|

Vol. 50, nr 4

567--577

EN

Diabetic macular edema (DME) is the dominant reason of diabetic visual loss, so early detection and treatment of DME is of great significance for the treatment of diabetes. Based on transfer learning, an automatic classification method is proposed to distinguish DME images from normal images in optical coherence tomography (OCT) retinal fundus images. Features of the DME are automatically identified and extracted by the pre-trained convolutional neural network (CNN), which only involves fine-tuning the VGGNet-16 network without any user intervention. An accuracy of 97.9% and a sensitivity of 98.0% are acquired with the OCT images in the Duke data set from experimental results. The proposed method, a core part of an automated diagnosis system of the DME, revealed the ability of fine-tuning models to train non-medical images, allowing them can be classified with limited training data. Moreover, it can be developed to assist early diagnosis of the disease, effectively delaying (or avoiding) the progression of the disease, consequently.

5

Education Quality Detection Method Based on the Probabilistic Neural Network Algorithm

Wu Changdong, Jiang Hua, Wang Ping

Diagnostyka

|

2020

|

Vol. 21, No. 4

79--86

EN

The traditional education quality detection method is too single and unreasonable, which is not suitable to evaluate students' ability comprehensively. In this paper, the probabilistic neural network (PNN) algorithm is used to detect the education quality by considering the important impact between the various achievements of students. PNN algorithm originates from Bayesian decision rule, and it uses the non-linear Gaussian Parzen window as the probability density function. As PNN model has the virtues of strong nonlinear and anti-interfering ability, it is fit to detect the education quality by classifying the students' achievements. Besides, the influences of different evaluation models on classification accuracy and efficiency are also discussed in this paper. Furthermore, the effect of spread value on PNN model is also discussed. Finally, the actual data are used to detect the education quality. Experimental results show that the detection accuracy can reach 95%, and the detection time is only 0.0156s based on the proposed method. That is to say, the method is a very practical detection algorithm with high accuracy and efficiency. Moreover, it also provides a reference for how to further improve the teaching quality.

6

Design and computation of a lightning protection system in an urban 110 kV substation

Taha Mohammed Ibrahim, Li Lin, Wang Ping

Archives of Electrical Engineering

|

2020

|

Vol. 69, nr 3

723--738

EN

A lightning protection system (LPS) of an urban 110 kV substation is designed and analysed according to NFPA 780 and IEC 62305-3 standards. The analysis of the LPS is established on the value of risk assessment. The total area of the plant is described by one soil layer with uniform resistivity. This study aims to improve the understanding of an unexpected manner of the grounding system beneath lightning currents by clarifying the basic concepts of the lightning protection level and the new design procedure in this paper was clarified according to NFPA-780 level 1 for a lightning protection system. The program is integrated with the CDEGS software, which provides effective geometrical modeling with object and result visualization. Furthermore, module and automated fast Fourier transform (FFT) is implemented in this study to simulate electromagnetic fields in the time and frequency domains. These current values are compared to the desired protection levels within the standards. The study results show that for the improved protection of the system against lightning, the total power grid must be considered as a source of improvement for studying shielding influence and the protection levels provided inside this substation.