Search

The control of soft surrounding rock stability has always been a hot academic issue. Soft rock has poor stability and low strength, and the deformation of a soft rock tunnel becomes more serious after it is affected by water for a long time. In this paper, the Jintong Coal Mine is taken as the research object, and nondestructive immersion experiments are used to study the change in mechanical properties of rock after being affected by water. The FLAC numerical model is used to analyze the stress evolution characteristics of the surrounding rock after being affected by water, and the results of the study show that the water absorption of siltstone is always higher than that of coarse-grained sandstone, and the uniaxial compressive strength of siltstone and coarse-grained sandstone decreases by 54.59% and 67.99%, respectively, under a state of saturated water compared with that under a state of dryness. Influenced by a T-shaped surface, the maximum principal stress concentration area occurs in the rock layer below the T-shaped surface and outside the joint. Concentrations of maximum shear stress occur within the “T” channel. Vertical stress concentration zones occur at the higher ground level and the bottom of the slope. The maximum shear stress of the roof fluctuates before the face reaches the surface of the “1” section, and continues to increase with and continues to increase with the distance of the face. After entering below the surface of the “1” section, the maximum shear stress of the roof increases rapidly, and the influence range is about 24 m. The maximum shear stress distribution plays a dominant role in the stability of the surrounding rocks of the two roadways. We analyze the principle of high-strength economic support, propose a “four-in-one” surrounding rock control technology based on “controlled hydrophobicity, structural adjustment, district management, and gradient control”, and propose a surrounding rock control scheme of district management. The measured data on site show that the roadway surrounding the rock is reasonably controlled. This provides a reference for the stable control of the surrounding rock of the roadway under similar conditions.

The reliability design of automotive structures is characterized by numerous variables and implicit responses. The traditional design of experiments for metamodel construction often requires manual adjustment of model parameters and extensive finite element analysis, resulting in inefficiency. To address these issues, active learning-based reliability methods are effective solutions. This study proposes an active-learning reliability analysis method based on multi-software interaction. Firstly, through secondary development of different software and MATLAB (version 2023a)’s batch processing function, a multi-software interactive reliability analysis method is developed, achieving automation in structural parametric design, finite element analysis and post-processing. This provides a more efficient and convenient platform for the implementation of active learning. Secondly, the polynomial chaos–kriging (PCK) active-learning method is introduced, combining the advantages of polynomial chaos expansion (PCE) and kriging. The PCK method captures the global behavior of the computational model using regression-based PCE and local variations using interpolation-based kriging. This metamodel is constructed with fewer training samples, effectively replacing the real multi-dimensional implicit response relations, thereby improving the efficiency of modeling and reliability analysis. Finally, the specific implementation scheme is detailed. The accuracy and efficiency of the proposed method are verified by a reliability engineering example of body-in-white bending and torsional stiffness.

In the digital era of increasing software complexity, improving the development efficiency of safety-critical software is a challenging task faced by academia and industry in domains such as nuclear energy, aviation, the automotive industry, and rail transportation. Recently, people have been excited about using pre-trained large language models (LLMs) such as ChatGPT and GPT-4 to generate code. Professionals in the safety-critical software field are intrigued by the code generation capabilities of LLMs. However, there is currently a lack of systematic case studies in this area. Aiming at the need for automated code generation in safety-critical domains such as nuclear energy and the automotive industry, this paper conducts a case study on generating safety-critical software code using GPT-4 as the tool. Practical engineering cases from the industrial domain are employed. We explore different approaches, including code generation based on overall requirements, specific requirements, and augmented prompts. We propose a novel prompt engineering method called Prompt-FDC that integrates basic functional requirements, domain feature generalization, and domain constraints. This method improves code completeness from achieving 30% functions to 100% functions, increases the code comment rate to 26.3%, and yields better results in terms of code compliance, readability, and maintainability. The code generation approach based on LLMs also introduces a new software development process and V-model lifecycle for safety-critical software. Through systematic case studies, we demonstrate that, with appropriate prompt methods, LLMs can auto-generate safety-critical software code that meets practical engineering application requirements. It is foreseeable that LLMs can be applied to various engineering domains to improve software safety and development efficiency.

The surge in malware threats propelled by the rapid evolution of the internet and smart device technology necessitates effective automatic malware classification for robust system security. While existing research has primarily relied on some feature extraction techniques, issues such as information loss and computational overhead persist, especially in instruction-level tracking. To address these issues, this paper focuses on the nuanced analysis of API (Application Programming Interface) call sequences between the malware and system and introduces TTDAT (Two-step Training Dual Attention Transformer) for malware classification. TTDAT utilizes Transformer architecture with original multi-head attention and an integrated local attention module, streamlining the encoding of API sequences and extracting both global and local patterns. To expedite detection, we introduce a two-step training strategy: ensemble Transformer models to generate class representation vectors, thereby bolstering efficiency and adaptability. Our extensive experiments demonstrate TTDAT’s effectiveness, showcasing state-of-the-art results with an average F1 score of 0.90 and an accuracy of 0.96.

Waste cement, a common by-product of urban construction, is often wasted in huge quantities and is worthless. However, some studies have confirmed that waste cement can be used as an alternative heavy metal immobilizing agent. Waste cements, derived from hydrated cement mortar products, were evaluated for soil Cd bioavailability by DTPA extraction and for their efficacy in ameliorating the toxicity of cadmium to soil enzymes and plant antioxidant enzymes. Soil incubation and pot experiments were conducted on three types of waste cement (OPC (ordinary Portland cement), FAC (fly ash cement) and ZEC (zeolite cement)) with an application rate of 1%, 2%, and 3%. The addition of OPC, FAC, and ZEC significantly increased the pH and cation exchange capacity of the soil (p < 0.05). The concentration of DTPA-extractable Cd significantly reduced with a consequential decrease in Cd uptake and transport in lettuce. OPC, FAC, and ZEC application significantly (p < 0.05) enhanced FDA hydrolysis and soil urease activity, except for catalase activity. OPC, FAC, and ZEC, when applied to soil, enhanced the total dry biomass (shoots and roots). Furthermore, the activities of guaiacol peroxidase (POD), catalase (CAT) and superoxide dismutase (SOD) declined in lettuce treated with OPC, FAC, and ZEC. With the addition OPC, FAC, and ZEC, the content of MDA in lettuce leaves displayed a remarkable decrease. In conclusion, the waste cements effectively reduced Cd bioavailability and enhanced the antioxidant system of lettuce.

Third-party library (TPL) reuse may introduce vulnerable or malicious code and expose the software, which exposes them to potential risks. Thus, it is essential to identify third-party dependencies and take immediate corrective action to fix critical vulnerabilities when a damaged reusable component is found or reported. However, most of the existing methods only rely on syntactic features, which results in low recognition accuracy and significantly discounts the detection performance by obfuscation techniques. In addition, a few semantic-based approaches face the efficiency problem. To resolve these problems, we propose and implement a more precise and scalable TPL detection method BBDetector. In addition to syntactic features, we consider the rich function-level semantic features and form a feature vector for each function. Moreover, we design a scalable function vector similarity search method to identify anchor functions and the candidate libraries, based upon which we carry out TPL detection. The experiment results demonstrate that BBDetector outperforms B2SFinder and ModX in terms of effectiveness, efficiency, and obfuscation-resilient capability. For the nix binaries, the F1-score of BBDetector is 1.11% and 11.21% higher than that of ModX and B2SFinder, respectively. Moreover, for the Ubuntu binaries, the F1-score of BBDetector is 1.32% and 14.93% is higher than that of ModX and B2SFinder, respectively. And in terms of efficiency, the detection time of BBDetector is only 30.02% of ModX. Besides, for the obfuscation-resilient capability, BBDetector is much stronger than B2SFinder. BBDetector achieves a F1-score of 71%, slightly lower than the F1-score of 77% achieved with the non-obfuscated binary programs. However, B2SFinder only achieves an F1-score of 28%, much lower than that of 67% achieved with the non-obfuscated binary programs.

Skeleton-based human action recognition has attracted extensive attention due to the robustness of the human skeleton data in the field of computer vision. In recent years, there is a trend of using graph convolutional networks (GCNs) to model the human skeleton into a spatio-temporal graph to explore the internal connections of human joints that has achieved remarkable performance. However, the existing methods always ignore the remote dependency between joints, and fixed temporal convolution kernels will lead to inflexible temporal modeling. In this paper, we propose a multi-scale adaptive aggregate graph convolution network (MSAAGCN) for skeleton-based action recognition. First, we designed a multi-scale spatial GCN to aggregate the remote and multi-order semantic information of the skeleton data and comprehensively model the internal relations of the human body for feature learning. Then, the multi-scale temporal module adaptively selects convolution kernels of different temporal lengths to obtain a more flexible temporal map. Additionally, the attention mechanism is added to obtain more meaningful joint, frame and channel information in the skeleton sequence. Extensive experiments on three large-scale datasets (NTU RGB+D 60, NTU RGB+D 120 and Kinetics-Skeleton) demonstrate the superiority of our proposed MSAAGCN.

Traditional malware classification relies on known malware types and significantly large datasets labeled manually which limits its ability to recognize new malware classes. For unknown malware types or new variants of existing malware containing only a few samples each class, common classification methods often fail to work well due to severe overfitting. In this paper, we propose a new neural network structure called ConvProtoNet which employs few-shot learning to address the problem of scarce malware samples while prevent from overfitting. We design a convolutional induction module to replace the insufficient prototype reduction in most few-shot models and generates more appropriate class-level malware prototypes for classification. We also adopt meta-learning scheme to make classifier robust enough to adapt unseen malware classes without fine-tuning. Even in extreme conditions where only 5 samples in each class are provided, ConvProtoNet still achieves more than 70% accuracy on average and outperforms other traditional malware classification methods or existed few-shot models in experiments conducted on several datasets. Extra experiments across datasets illustrate that ConvProtoNet learns general knowledge of malware which is dataset-invariant and careful model analysis proves effectiveness of ConvProtoNet in few-shot malware classification.