Penetration rate prediction for hard rock tunnel boring machines (TBMs) remains challenging because rock mass conditions and machine operating regimes vary continuously along the tunnel alignment. Conventional static prediction models may not adequately represent such non-stationary construction conditions, particularly when geotechnical measurements are incomplete or obtained with delay during excavation. This study aims to develop a construction-phase prediction framework for ring-scale TBM penetration rate in a granite tunnel drive by integrating geotechnical data completion, sequence deep learning, and rolling-window model evaluation. A dataset of 1,000 consecutive rings was compiled, including boring-only penetration rate, thrust, torque, cutterhead rotational speed, rock mass type, and uniaxial compressive strength (UCS). Missing UCS measurements were completed using inverse distance weighting within a block model representation, resulting in estimated UCS values of approximately 33–177 MPa for rock masses dominated by massive and fractured granite. Three sequence deep learning models, namely long short-term memory (LSTM), gated recurrent unit (GRU), and temporal convolutional network (TCN), were evaluated using root mean square error (RMSE), mean absolute error (MAE), and a symmetric ±10% tolerance band adapted from accuracy-band concepts used in AACE-based project controls. The proposed rolling protocol used 100-ring validation and 100-ring test blocks to assess predictive performance under changing ground conditions. The results show that the optimized GRU model provided the most robust overall performance, achieving a mean test RMSE of approximately 0.229 m/h and a mean within-band compliance of approximately 54% across rolling folds. These findings indicate that rolling-window sequence learning can provide a practical and adaptable framework for construction-phase TBM performance prediction under evolving geological and operational conditions.
Friction is a ubiquitous physical phenomenon in nature and daily life. The demand for energy conservation and green development in industrial development has led to increasing attention being paid to tribology research. Despite significant achievements in tribology, many friction problems remain unsolved, particularly the lack of a unified friction theory applicable to all friction issues. The fundamental conditions for occurrence of friction are contact and relative motion between two surfaces, so the advancement of contact theories has significantly contributed to the development of tribology. Not only the models of contact theory across different scales in the past development of tribology were reviewed in this paper, also the assumptions and applicability limitations of each model were summarized and compared. The limitations of theoretical calculations of friction-contact research have been concerned. Now the study of contact mechanics and tribology is facing new opportunities for further progress under the era of the emergence of the big data and artificial intelligence based on sufficient data and computing power. The preliminary prospect on the research of tribology has been carried out. A novel research strategy that combines artificial intelligence, experimentation, and contact theory was proposed to investigate the contact problem in tribology field. This strategy may also be online collaborative research between different research groups all over the world.
Ensuring reliable camera vision in autonomous driving systems requires continuous monitoring of image quality and lens integrity. External contaminants such as dust, raindrops, and mud, as well as permanent defects like cracks or scratches, can severely degrade visual perception and compromise safety-critical tasks such as lane detection, obstacle recognition, and path planning. This paper presents an AI-based framework that integrates image quality assessment (IQA) and lens defect analysis to enhance the robustness of camera-based perception systems in autonomous vehicles. Building on previous conceptual work in safety-aware lens defect detection, the proposed framework introduces a dual-layer architecture that combines real-time IQA monitoring with deep learning-based soiling segmentation. As an initial experimental validation, a U-Net model was trained on the WoodScape Soiling dataset to perform pixel-level detection of lens contamination. The model achieved an average Intersection-over-Union (IoU) of 0.6163, a Dice coefficient of 0.7626, and a recall of 0.9780, confirming its effectiveness in identifying soiled regions under diverse lighting and environmental conditions. Beyond the experiment, this framework outlines pathways for future integration of semantic segmentation, anomaly detection, and safety-driven decision policies aligned with ISO 26262 and ISO 21448 standards. By bridging conceptual modeling with experimental evidence, this study establishes a foundation for intelligent camera health monitoring and fault-tolerant perception in autonomous driving. The presented results demonstrate that AI-based image quality and defect assessment can significantly improve system reliability, supporting safer and more adaptive driving under real-world conditions.
The development and implementation of energy and resource-saving types of machinery and equipment for agricultural activities in crop fields dedicated to vegetable cultivation is gaining a leading position worldwide. "Considering that vegetable crops are cultivated on over 58.2 million hectares globally it is a crucial task to introduce high-performance, modern technical means for fertilizing vegetable crops and inter-row cultivation. In this regard, special attention is being paid to using compact, low-energy-consuming technical means that allow for increasing the efficiency of fertilizer use in vegetable cultivation and applying them to the specified depth and width. World-wide, research and development efforts are underway to develop new scientific and technical solutions for resource-saving technical means that apply fertilizers locally and work in open conditions for inter-row cultivation, with the aim of reducing the amount of applied fertilizers and increasing their effectiveness in preserving the natural properties of vegetables. In this direction, particular attention is paid to developing a drill coulter design that ensures the operation of working bodies in open conditions to reduce energy consumption during local fertilizer application and inter-row cultivation in a single pass for onions, as well as scientifically substantiating the technological processes and parameters they performed. This article presents the results of theoretical studies conducted on the movement of mineral fertilizers from the metering device through the fertilizer conduit. The main factors affecting the movement of mineral fertilizers in the fertilizer conduit are analyzed. Based on the research, graphs illustrating the change in the fertilizer exit rate from the conduit over time are constructed. Based on the results obtained, scientifically based recommendations for uniform fertilizer application are provided. The length of the fertilizer tube and the angles of the guide installation can be selected depending on the speed of the fertilizer machine, the falling distance of the fertilizer, and the application rate.
This article presents a comprehensive analysis of the wear behavior of G-shaped blades used in milling cultivators under controlled laboratory conditions. The study specifically focuses on evaluating how various operational factors influence the wear intensity of the blade material. Among the key parameters analyzed are the applied pressure force, the total duration of the testing process, the linear friction speed between the blade surface and the abrasive medium, as well as the rate of abrasive material consumption throughout the test cycle. The laboratory experiments were designed to simulate realistic working conditions to which the blades are typically subjected during soil cultivation operations. By systematically varying the pressure force applied to the blade samples, the researchers were able to observe and quantify the correlation between increasing load and material wear rate. Higher pressure levels generally led to a more intense abrasion effect, highlighting the critical importance of optimizing operational loads during field use. Another significant factor investigated was the testing duration. It was observed that prolonged exposure of the blade materials to abrasive interaction progressively increased the wear depth, which directly correlates with reduced blade service life. This finding underscores the necessity of selecting materials with enhanced wear resistance for longer operational cycles.
