Search

Name Entity Recognition (NER) aims to recognize entities in the engine room domain from unstructured engine room domain text. But in the engine room domain, the entities are diverse and complex, and there is a nesting phenomenon, resulting in a low entity recognition rate. In this paper, a deep learning method incorporating language models is proposed to enhance the entity recognition performance within the engine room. domain. Firstly, the Bidirectional Encoder Representation from Transformers (BERT) language model is employed to train text feature extraction, acquiring a matrix of vector representations at the word level. Secondly, the trained word vectors are fed into the Bidirectional Gated Recurrent Unit (BiGRU) for contextual semantic entity feature extraction. Finally, the global optimal sequence is extracted by combining with the Conditional Random Field (CRF) model to obtain the named entities in the ship cabin semantics. The experimental results show that the proposed algorithm can obtain better F1 values for all three types of entity recognition. Compared with BERT-BiGRU, the overall accuracy of entity identification, recall rate and F1 value are improved by 1.35%, 1.45% and 1.40%, respectively.

The traditional approach to ship pipeline programming often involves describing and calculating based on text files. This method tends to be error-prone and time-consuming, especially for complex systems with a large amount of data related to pipelines. In case of system failures, troubleshooting becomes inconvenient. Additionally, matrix calculations can lead to issues such as extreme values, and visualizing the results is challenging. To address these challenges, this paper proposes an intuitive, user-friendly, and efficient ship pipeline programming tool. The tool utilizes Microsoft’s WPF (Windows Presentation Foundation) graphical interface technology and the C# programming language. A graphical interface for ship pipeline networks is constructed, allowing users to visually build the physical model of pipelines through intuitive drag-and-drop and connection operations. Furthermore, the paper adopts Excel spreadsheets as the input method for data and combines it with domain knowledge of marine engineering pipelines. This approach establishes logical models for various pipelines, valves, and other equipment on ships. The models incorporate attributes from the spreadsheet to control characteristics like maximum flow rates and flow directions. By combining graphical modules, pipeline connections, and Excel spreadsheets, the method proposed in this paper offers a more convenient way to construct pipeline network models. The resulting models closely resemble actual ship pipelines, leading to improved accuracy and efficiency in data processing and calculations.

With the aim of solving warp tension control problems in the let-off system and opening system in the carbon fiber multilayer diagonal loom, dynamic models of warp tension are established in this study based on dynamic analysis. Adaptive fuzzy PID control is applied to the tension-networked control, and an adaptive fuzzy PID controller is designed to solve the problems of network induced delay, packet loss, and network bandwidth occupancy. A TrueTime simulation structure of the tension control system is also built. Compared with PID control, adaptive fuzzy PID control exhibited the advantages of a small overshoot, small fluctuation of output tension, good tracking effect, and stability in simulations under different conditions, including a 30-ms network induced delay, 10% packet loss, and 30% network bandwidth occupancy. The results of the simulations show that adaptive fuzzy PID control has better control effect than PID control, and is more suitable for tension-networked control systems in the carbon fiber multilayer diagonal loom.

Automatic detection of violent videos has broad application prospects in many fields such as video surveillance and movie grading. However, most existing violent video detection models based on multimodal feature fusion ignore the fact that the audio-visual data in the same violent video may not semantically correspond. Blindly fusing non-corresponding features is not beneficial even potentially harmful to models. In this paper, we propose a novel violent video detection model based on semantic correspondence between audio-visual data from the same video. Deep neural networks are used to extract features of three different modalities: appearance, motion, and audio. After that, we choose the feature-level fusion strategy to fuse these multimodal features via shared subspace learning. Semantic correspondence is used to guide this process through multitask learning and semantic embedding learning. To evaluate the effectiveness of our model, we conduct experiments on several public datasets and our self-built dataset: Violence Correspondence Detection. The results show that our model achieves quite competitive results on both.

The two-layer distributed control architecture, including the microgrid (MG) control layer and MG cluster (MGC) control layer, can be used for interconnecting multiple MGs to form the MGC. However, the coupling among multiple elements and the interaction between two control layers may introduce new low-damping oscillatory modes and even reduce the stability margin. Unfortunately, the detailed small-signal stability analysis and stability enhancement method of the MGC with the two-layer distributed control strategy have not been reported. To fill this gap, this paper first presents a unified small-signal dynamic model of the MGC. Subsequently, a comprehensive small-signal stability analysis based on the model is presented to analyze: 1) the mechanism of coupling/interaction among MGs and multiple control layers; 2) the participation factors of the low-damping modes; and 3) the sensitivity of the distributed control parameters. Moreover, the design of the distributed control parameters is formulated as an optimization problem, where the particle swarm optimization is employed to search for an optimal combination of parameters to enhance system stability. Finally, the stability assessment and time-domain simulation are carried out to validate the effectiveness of the proposed method.