Search Results (5)

The current network for the dual-task grinding wheel defect semantic segmentation lacks high-precision lightweight designs, making it challenging to balance lightweighting and segmentation accuracy, thus severely limiting its practical application in grinding wheel production lines. Additionally, recent approaches for addressing the natural class imbalance in defect segmentation fail to leverage the inexhaustible unannotated raw data on the production line, posing huge data wastage. Targeting these two issues, firstly, by discovering the similarity between Coordinate Attention (CA) and ASPP, this study has introduced a novel lightweight CA-ASP module to the DeeplabV3+, which is 45.3% smaller in parameter size and 53.2% lower in FLOPs compared to the ASPP, while achieving better segmentation precision. Secondly, we have innovatively leveraged the Masked Autoencoder (MAE) to address imbalance. By developing a new Hybrid MAE and applying it to self-supervised pretraining on tremendous unannotated data, we have significantly uplifted the network’s semantic understanding on the minority classes, which leads to further rises in both the overall accuracy and accuracy of the minorities without additional computational growth. Lastly, transfer learning has been deployed to fully utilize the highly related dual tasks. Experimental results demonstrate that the proposed methods with a real-time latency of 9.512 ms obtain a superior segmentation accuracy on the mIoU score over the compared real-time state-of-the-art methods, excelling in managing the imbalance and ensuring stability on the complicated scenes across the dual tasks. Full article

Port operations have been suffering from hybrid uncertainty, leading to various disruptions in efficiency and tenacity. However, these essential uncertain factors are often considered separately in literature during berth and quay crane assignments, leading to defective, even infeasible schedules. This paper addressed the integrated berth allocation and quay crane assignment problem (BACAP) with stochastic vessel delays under different conditions. A novel approach that combines both proactive and reactive strategies is proposed. First, a mixed-integer programming model is formulated for BACAP with quay crane maintenance activities under the ideal state of no delay. Then, for minor delays, buffer time is added to absorb the uncertainty of the arrival time of vessels. Thus, a robust optimization model for minimizing the total service time of vessels and maximizing the buffer time is developed. Considering that the schedule is infeasible when a vessel is seriously delayed, a reactive model is built to minimize adjustment costs. According to the characteristics of the problem, this article combined local search with the genetic algorithm and proposed an improved genetic algorithm (IGA). Numerical experiments validate the efficiency of the proposed algorithm with CPLEX and Squeaky Wheel Optimization (SWO) in different delay conditions and problem scales. An in-depth analysis presents some management insights on the coefficient setting, uncertainty, and buffer time. Full article

The condition of a railway vehicle’s wheels is an essential factor for safe operation. However, the current inspection of railway vehicle wheels is limited to periodic major and minor maintenance, where physical anomalies such as vibrations and noise are visually checked by maintenance personnel and addressed after detection. As a result, there is a need for predictive technology concerning wheel conditions to prevent railway vehicle damage and potential accidents due to wheel defects. Insufficient predictive technology for railway vehicle’s wheel conditions forms the background for this study. In this research, a real-time tire wear classification system for light-rail rubber tires was proposed to reduce operational costs, enhance safety, and prevent service delays. To perform real-time condition classification of rubber tires, operational data from railway vehicles, including temperature, pressure, and acceleration, were collected. These data were processed and analyzed to generate training data. A 1D–CNN model was employed to classify tire conditions, and it demonstrated exceptionally high performance with a 99.4% accuracy rate. Full article

In this paper, Fe-based and Co-based alloy powders were chosen to perform laser cladding on wheel materials through conventional laser cladding (CLC) and ultra-high-speed laser cladding (UHSLC) processes, respectively. The microstructures, element distribution, phase composition and hardness of the Fe-based alloy and Co-based alloy coating layers using the CLC and UHSLC processes were compared and analysed. The results show that the CLC and UHSLC alloy coatings were dense and free of defects such as pores and cracks. Compared with the CLC alloy coating, the grain size of the UHSLC alloy coating was smaller, the coating composition was close to the powder design composition, and the distribution of Cr within and between the grains was more uniform. The Fe-based coating was mainly composed of (Fe, Ni) and Cr₇C₃, and the Co-based coating was mainly composed of γ-Co and Cr₂₃C₆. It was found that the cooling rate of the CLC alloy coating was smaller than that of the USHLC, and the hardness of the CLC alloy coating was less than that of the USHLC. The average hardness of the UHSLC Fe-based and Co-based alloy coatings was 709 HV and 525 HV, respectively. The average hardness of the CLC Fe-based and Co-based alloy coatings was 615 HV and 493 HV, respectively. The rolling friction and wear tests were carried out with the CLC-treated and UHSLC-treated wheel specimens on the GPM-30 rolling contact fatigue testing machine. The results showed that the wear rate of the UHSLC alloy coating on the wheel specimens was significantly lower than that of the CLC alloy coating on the wheel specimens. The wear rates of the UHSLC Fe-based and Co-based alloy coatings on the wheel specimens were reduced by 40.7% and 73.8%, respectively. It was demonstrated that the wear resistance of the USHLC alloy coatings was better than those of the CLC alloy coatings. The CLC alloy coating exhibited more severe fatigue damage with small cracks. Furthermore, the damage of the UHSLC alloy coating was relatively minor, with slight spalling. The Co-based alloy coating exhibited superior wear properties with the same laser cladding process. Full article

For high-speed trains, out-of-roundness (OOR)/defects on wheel tread with small radius deviation may suffice to give rise to severe damage on both vehicle components and track structure when they run at high speeds. It is thus highly desirable to detect the defects in a timely manner and then conduct wheel re-profiling for the defective wheels. This paper presents a wayside fiber Bragg grating (FBG)-based wheel condition monitoring system which can detect wheel tread defects online during train passage. A defect identification algorithm is developed to identify potential wheel defects with the monitoring data of rail strain response collected by the devised system. In view that minor wheel defects can only generate anomalies with low amplitude compared with the wheel load effect, advanced signal processing methods are needed to extract the defect-sensitive feature from the monitoring data. This paper explores a Bayesian blind source separation (BSS) method to decompose the rail response signal and to obtain the component that contains defect-sensitive features. After that, the potential defects are identified by analyzing anomalies in the time history based on the Chauvenet’s criterion. To verify the proposed defect detection method, a blind test is conducted using a new train equipped with defective wheels. The results show that all the defects are identified and they concur well with offline wheel radius deviation measurement results. Minor defects with a radius deviation of only 0.06 mm are successfully detected. Full article