Wen Y Ma

Prof. Dr. Wen Y Ma


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
WMWen Y Ma
Wen Y Ma
WHWang Hongbo
Wang Hongbo
WYwang sheng yin
wang sheng yin
Collision-risk measurements are crucial for ships, as they are necessary for collision avoidance decision making. However, collision risks between ships have not been quantified in unified standards. In this study, a critical collision index is proposed to describe the critical degree of collision risks between ships. Based on the field theory, a collision-risk field was introduced to build a field strength model based on the collision index. The model synthetically considers the influences of distance at closest point of approach, time to closest point of approach, and the relative bearing of coming ships. Moreover, the real time to the closest point of approach was used for describing the collision risk between ships. In addition, encounter situations and collision risks in the field were simulated using the field strength model and isorisk lines. The results are in agreement with the real collision-risk perceptions of Officers on Watch. It was shown that the proposed ship critical collision index can play an important role in ship collision avoidance and early warning systems.

Verified
Journal Article
Open access
PDF file
WMWenyao Ma
Wenyao Ma
WMWen Y Ma
Wen Y Ma
With the rapid growth of the global shipping industry and the increasing availability of Automatic Identification System (AIS) data, accurate vessel trajectory prediction has become crucial for ensuring navigational safety and optimizing maritime traffic management. This paper presents a systematic review of recent advances in deep learning-based methods for vessel trajectory prediction. We provide a comprehensive analysis of mainstream models, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs) such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, Sequence-to-Sequence (Seq2Seq) models, and the Transformer architecture. Their performance is compared in terms of spatio-temporal data processing capability, prediction accuracy, and computational efficiency. Furthermore, this review examines practical applications of these methods in scenarios such as collision avoidance and route optimization. Despite notable progress, several challenges remain, including data quality issues, real-time prediction capability, and model interpretability. Future research directions may focus on multi-source data fusion and the development of lightweight model designs to further improve prediction performance. This survey aims to serve as a valuable reference for researchers and contribute to ongoing innovation in vessel trajectory prediction technology.

24 August 2024 in Processes
Verified
Journal Article
Open access
PDF file
YWyuanqing wang
yuanqing wang
WMWen Y Ma
Wen Y Ma
A system combining gas-phase oxidation and liquid-phase collision absorption for removing NO from marine diesel engine exhaust was proposed. This method was the first to utilize different physical states of the same mixed solution to achieve both pre-oxidation and impingement reduction absorption of exhaust gases. During the pre-oxidation stage, a mixture of (NH4)2S2O8 and urea solution was atomized into a spray using an ultrasonic nebulizer to increase the contact area between the oxidant and the exhaust gas, thereby efficiently pre-oxidizing the exhaust gas in the gas phase. In the liquid-phase absorption stage, the (NH4)2S2O8 and urea solution was used in an impingement absorption process, which not only enhanced gas–liquid mass transfer efficiency but also effectively inhibited the formation of nitrates. Experimental results showed that, without increasing the amount of absorbent used, the maximum NO removal efficiency of this method reached 97% (temperature, 343 K; (NH4)2S2O8 concentration, 0.1 mol/L; urea concentration, 1.5 mol/L; NO concentration, 1000 ppm; pH, 7; impinging stream velocity, 15 m/s), compared to 72% using the conventional liquid-phase oxidation absorption method. Additionally, this method required only the addition of a nebulizer and two opposing nozzles to the existing desulfurization tower to achieve simultaneous removal of sulfur and nitrogen oxides from the exhaust gas, with low retrofitting costs making it favorable for practical engineering applications.

2 March 2026 in Scientific Reports
Verified
Journal Article
Open access
YWYuanqing Wang
Yuanqing Wang
JCJuan Chen
Juan Chen
WMWen Y Ma
Wen Y Ma
This paper addresses the predefined-time adaptive fuzzy control problem for non-strict feedback nonlinear systems (NSFNS) with input quantization. First, a novel inverse hyperbolic sine state observer was designed based on fuzzy logic to estimate unmeasurable states. Second, owing to the non-smooth and non-differentiable nature of the quantized output signal, a predefined-time differentiator method was proposed to concurrently handle these issues and reduce control signal fluctuations. Theoretical analysis demonstrates that the observer-based output feedback closed-loop system achieves practical predefined-time stability (PPTS): all signals are bounded, and the tracking error converges to a neighborhood of zero within the desired settling time [Formula: see text], with the observation error suppressed to a negligible bounded region simultaneously. Finally, a simulation example verifies the effectiveness of the proposed scheme.

9 December 2024 in Symmetry
Verified
Journal Article
Open access
PDF file
YWyuanqing wang
yuanqing wang
WMWen Y Ma
Wen Y Ma
GZGuichen Zhang
Guichen Zhang
A novel, precise disturbance rejection dynamic inversion control algorithm has been proposed. In the high-order dynamic surface control system, an innovative approach utilizes a monotonically increasing inverse hyperbolic sine function to construct an extended state observer, which estimates the uncertain functions at each step. The monotonicity of the inverse hyperbolic sine function simplifies the system stability analysis. Additionally, being a smooth function, it avoids the disturbances caused by piecewise functions at their breakpoints in conventional observer construction, thereby enhancing system stability. The accurate prediction capability of the new observer improves the system’s disturbance rejection performance. To address the inherent differential explosion phenomenon in traditional dynamic inversion control schemes, this paper ingeniously employs a tracking signal observer as a substitute for traditional filters, thus avoiding the differential explosion that may occur with first-order filters. Finally, comparative simulations were conducted to validate the effectiveness of the proposed method. The results show that both the observer and the controller possess high-gain characteristics, and the closed-loop system exhibits a fast convergence rate.