Peng Yang

Dr. Peng Yang

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 April 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
PYPeng Yang
Peng Yang
BZBozheng Zhang
Bozheng Zhang
JZJianda Zhao
Jianda Zhao
To address the issue of low efficiency in feature extraction and model training when traditional deep learning methods handle long time-series data, this paper proposes a Time-Series Lightweight Transformer (TSL-Transformer) model. According to the data characteristics of bearing fault diagnosis tasks, the model makes lightweight improvements to the traditional Transformer model, and focuses on adjusting the encoder module (core feature extraction module), introducing multi-head attention mechanism and feedforward neural network to efficiently extract complex features of vibration signals. Considering the rich temporal features present in vibration signals, a Long Short-Term Memory (LSTM) module is introduced in parallel to the encoder module of the improved lightweight Transformer model. This enhancement further strengthens the model’s ability to capture temporal features, thereby improving diagnostic accuracy. Experimental results demonstrate that the proposed TSL-Transformer model achieves a fault diagnosis accuracy of 99.2% on the CWRU dataset. Through dimensionality reduction and visualization analysis using the t-SNE method, the effectiveness of different network structures within the proposed TSL-Transformer model is elucidated.

10 February 2025 in Systems
Verified
Journal Article
Open access
PDF file
XYXiaoqin Ye
Xiaoqin Ye
PYPeng Yang
Peng Yang
With the increasing importance of renewable energy in the global energy transition, the microgrid has attracted wide attention as an efficient and flexible power solution. However, there are some problems in current networked microgrid systems, such as complex structure, numerous parameters, and significant fluctuations in generation capacity. Aiming at the parameter optimization problem of networked microgrids integrating multiple energy generation and energy storage forms, this paper constructs a multi-objective microgrid structure decision-making model. The model comprehensively considers operation and maintenance costs, fuel costs, power abandonment and lack-of-power punishment costs, power transaction costs, and pollution treatment costs, aiming to realize the joint optimization of economic benefits and environmental sustainability. Furthermore, an improved multi-objective particle swarm optimization (IMOPSO) algorithm is designed to solve the model. In order to verify the effectiveness of the model in the scenarios of distributed energy and energy load fluctuation, this paper uses the scenario analysis method to realize the data analysis of 2000 scenarios, and obtains four typical deterministic scenarios for simulation experiments. The experimental results show that, compared with the traditional microgrid, when the capacity configuration is determined by the number of wind driven generators, photovoltaic panels, diesel generators, and batteries being 5, 189, 2, and 107, respectively, the proposed net-connected economic dispatch optimization method based on hybrid renewable energy in this paper reduces the generation cost and environmental cost of the system by 96.76 ¥ to 428.19 ¥, and keeps the load loss rate stable between 0.34% and 4.56%. The utilization rate of renewable energy has been raised to about 95%.

29 March 2025 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
PYPeng Yang
Peng Yang
BZBozheng Zhang
Bozheng Zhang
KSKai Shi
Kai Shi
YHYi Hui
Yi Hui

31 January 2025 in Systems
Verified
Journal Article
Open access
PDF file
PYPeng Yang
Peng Yang
BZBozheng Zhang
Bozheng Zhang
JYJingRong Yang
JingRong Yang
The layout of emergency medical services (EMS) is of vital importance. A well-planned layout significantly impacts the timeliness of response and operational efficiency, which are crucial for saving lives and mitigating injury severity. This paper presents a novel decision support framework for optimizing EMS station layout. Employing the k-means clustering algorithm in combination with the elbow method and silhouette coefficient method, we conduct a clustering analysis on a patient call record dataset. Comprising 166,161 emergency center call records in the Shanghai area over one year, this dataset serves as the basis for our analysis. The analysis results are applied to determine EMS station locations, with the average ambulance patient pickup time as the evaluation criterion. A simulation model is utilized to validate the effectiveness and reliability of the decision-making framework. An experimental analysis reveals that compared with the existing EMS station layout, the proposed framework reduces the average patient pickup time from 11.033 min to 9.661 min, marking a 12.441% decrease. Furthermore, a robustness test of the proposed scheme is carried out. The results indicate that even when some first-aid sites fail, the average response time can still be effectively controlled within 9.9 min. Through this robustness analysis, the effectiveness and reliability of the decision framework are demonstrated, offering more efficient and reliable support for the EMS system.

8 December 2023
Verified
Conference Paper
Open access
SYShisong Yang
Shisong Yang
PYPeng Yang
Peng Yang
TWTeng Wu
Teng Wu
With the widespread application of satellite communication systems and the explosive growth of mobile terminals, various demands have brought considerable pressure to the satellite communication system. There are many network stability and security issues in the satellite communication process, leading to the proposal of a non-cooperative game-based satellite network communication method. Both sides engage in non-cooperative games: during the attack and defense process of the satellite communication network, the attacking side exploits vulnerabilities in the satellite communication network system to maximize the attack effect, taking a series of attack actions to achieve a certain goal of disrupting the communication network system. The defense side, in response to the performance requirements of the satellite communication network system and the attacks it faces, takes a series of defense actions [3]. The antagonism, non-cooperation, and high degree of strategic dependence in communication network attacks and defenses are closely related to game theory. After the attack and defense process begins, the attacking side continuously adjusts the next round of attack strategy based on the attacks launched and the gains obtained, while the defense side, to maximize its own gains, will maintain smooth satellite network communication as much as possible based on the contract routing algorithm.

27 May 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
SWSheng Wang
Sheng Wang
JYJingrong Yang
Jingrong Yang
PYPeng Yang
Peng Yang
Emergency rescue path planning faces severe challenges due to the uncertainty of the road network and the complexity of road damage following mass casualty incidents (MCIs) such as earthquakes. Traditional static path planning algorithms struggle to cope with such dynamic environments, while standard reinforcement learning methods often cause agents to fall into local optima, failing to meet rescue safety requirements. To address this dilemma, this paper proposes an improved Q-learning algorithm that integrates Adaptive Simulated Annealing (ASA) and Experience Replay (ER) mechanisms. The algorithm dynamically regulates the exploration degree via the ASA strategy, ensuring the agent can escape local traps in complex damaged environments. Furthermore, it incorporates the ER mechanism to reuse key path experiences, thereby improving convergence speed. Experimental results demonstrate that the proposed method demonstrates efficient online re-planning capabilities in response to structural environmental updates. It provides high-confidence decision support for time-critical post-disaster rescue, balancing the trade-off between accessibility and safety.