With the continuous development of industries such as wind power and construction, the weight and complexity of lifted equipment have significantly increased. These lifting tasks often rely on crawler cranes, and the demand for cooperative lifting using dual crawler cranes has grown. However, current operations remain largely manual, leading to safety risks and low efficiency. While extensive research has been conducted on the coordination of overhead cranes and other lifting systems, studies on cooperative control of crawler cranes are still in their early stages and have received insufficient attention. To address this issue, this paper establishes an accurate model of a dual crawler crane system using Lagrange equations. Motion constraints are incorporated to reduce the original fifth-order dynamics to a third-order system, simplifying control implementation. Given the strong coupling characteristics of the underactuated system, a PID-based coupled error compensation control method is proposed to regulate the load’s position and attitude precisely. By coordinating cable length adjustments, the proposed method ensures stable and accurate positioning while guaranteeing finite time convergence of cable length errors. Finally, a wind turbine installation scenario is simulated to validate the effectiveness of the proposed control approach.

As a key component of industrial equipment, bearings are prone to failure under complex operating conditions. Bearing fault diagnosis can detect potential dangers at an early stage, thus ensuring the stability and efficiency of production. Existing research mainly focuses on the structural improvement of the fault classification model and often neglects the optimization of the algorithm parameters. To address this deficiency, this paper proposed a hybrid convolutional neural network-long short-term memory (CNN-LSTM) model for bearing fault diagnosis. The model parameters were optimized using the improved whale optimization algorithm (IWOA). Experimental results show that the proposed method has superior performance in bearing fault diagnosis and has broad application prospects.

Rust is a system programming language that emphasizes both efficiency and memory safety. It achieves comparable efficiency with C/C++ by pursuing the concept of zero-cost abstraction and memory safety via its ownership scheme. As a side effect, these features may also steepen the learning curve for developers, potentially leading to the use of inefficient code in their programs. In this paper, we aim to investigate the characteristics of performance bugs that occur in real-world Rust projects. To this end, we have mined the repository of 100 well-known projects on GitHub and collected 114 performance bugs. We manually audit each case and find 8 optimization patterns unique to Rust, including three types of checking, two types of cloning, and three types of data collection. We have further designed a static analyzer for Rust-specific patterns and evaluated it through two complementary experiments: (1) a controlled micro-benchmark across 48 cases, demonstrating strong detection capability for optimizable patterns like bounds checking, and (2) a large-scale validation on 5 real-world projects (7k functions, 50K LOC) confirming practical applicability. The results advocate a tiered optimization strategy: automated fixes for less context-sensitive patterns and developer-guided solutions for complex cases like cloning. We hope our work can enhance the usability of Rust’s complex yet powerful language features, empowering developers to write safe, high-performance code more efficiently.

Rust is a system programming language that emphasizes both efficiency and memory safety. It achieves comparable efficiency with C/C++ by pursuing the concept of zero-cost abstraction and memory safety via its ownership scheme. As a side effect, these features may also steepen the learning curve for developers, potentially leading to the use of inefficient code in their programs. In this paper, we aim to investigate the characteristics of performance bugs that occur in real-world Rust projects. To this end, we have mined the repository of 100 well-known projects on GitHub and collected 122 performance bugs. We showcase two main findings including performance issues from Rust's dynamic checking and memory management mechanisms. We hope our work can enhance the usability of Rust's complex yet powerful language features, empowering developers to write safe, high-performance code more efficiently.

Dialogue summarization aims to condense a given dialogue into a simple and focused summary text.Typically, both the roles' viewpoints and conversational topics change in the dialogue stream.Thus how to effectively handle the shifting topics and select the most salient utterance becomes one of the major challenges of this task.In this paper, we propose a novel topic-aware Global-Local Centrality (GLC) model to help select the salient context from all sub-topics.The centralities are constructed at both the global and local levels.The global one aims to identify vital sub-topics in the dialogue and the local one aims to select the most important context in each sub-topic.Specifically, the GLC collects sub-topic based on the utterance representations.And each utterance is aligned with one sub-topic.Based on the sub-topics, the GLC calculates globaland local-level centralities.Finally, we combine the two to guide the model to capture both salient context and sub-topics when generating summaries.Experimental results show that our model outperforms strong baselines on three public dialogue summarization datasets: CSDS, MC, and SAMSUM.Further analysis demonstrates that our GLC can exactly identify vital contents from sub-topics. 1

Natural language video localization (NLVL) aims to locate the matching span relevant to a given query sentence from an untrimmed video. This task requires not only understanding video and text but also aligning the semantics between video and language. Existing methods obtain vision-language representations via separate encoders, cross-modal interactions are not fine-grained enough, and the semantics are not fully aligned. In this paper, we address the vision-language alignment via joint modeling and contrastive learning. We propose a unified Video-Language Representation Network (UniNet), employing a transformer encoder to learn vision-language representations aligned. Simultaneously taking video and text as input, the encoder jointly learns the representations of both and captures the inter-relations between video and text. Then the representations are used by the predictor to locate the grounding video span. Besides, we train our model with contrastive learning to enhance vision-language representations in the training stage. Experiments on three benchmark datasets show that UniNet outperforms the baseline methods and adopting unified representation and contrastive learning can improve vision-language semantic alignment.