Purpose-Weathering steel has excellent resistance to atmospheric corrosion,but still faces complex environmental corrosion problems during long-term operation.This paper mainly studies the corrosion problem of weather...Purpose-Weathering steel has excellent resistance to atmospheric corrosion,but still faces complex environmental corrosion problems during long-term operation.This paper mainly studies the corrosion problem of weather resistant steel materials for railway freight car bodies with a load capacity of 70 tons.Design/methodology/approach-The paper analyzes the corrosion characteristics of weather resistant steel materials for truck bodies through macroscopic and microscopic methods including metallographic microscopy,scanning electron microscopy,energy dispersive spectroscopy and X-ray diffraction.Electrochemical analysis shows that the rust layer on the surface of weathering steel changes the surface state of the material,and also proves that weathering steel used in trucks undergoes electrochemical corrosion under atmospheric corrosion.At the same time,ion chromatography technology is used to study the corrosive ions mainly present in the residual liquid and foam solution inside the vehicle body.Findings-The corrosion of truck body materials is mainly electrochemical corrosion,and the corrosion of door materials is more obvious than that of other parts.The corrosion products are mainly Fe oxides and hydroxides.There are high concentrations of Cl-and SO42-ions in the residual liquid and foam solution at the bottom of the freight car,which are the main factors causing corrosion of the railway freight car body.Originality/value-The foam adhesive around the door panel is in a moist state for a long time,and corrosive ions will accelerate the electrochemical corrosion of the weather resistant steel material of the door panel.Therefore,the corrosion of the cargo door panel is more severe than other components.展开更多
To address the issue of accurately extracting fault characteristic information of railway freight car bearings under noisy conditions,this paper proposes a fault diagnosis method based on Adaptive Chirp Mode Decomposi...To address the issue of accurately extracting fault characteristic information of railway freight car bearings under noisy conditions,this paper proposes a fault diagnosis method based on Adaptive Chirp Mode Decomposition(ACMD)and an optimized Maximum Correlation Kurtosis Deconvolution(MCKD)using a Sparrow Search Algorithm Combining Sine-Cosine and Cauchy Mutation(SCSSA).Firstly,ACMD is used to decompose and reconstruct the original fault signal to obtain several Intrinsic Mode Functions(IMFs).Then,the IMFs are filtered according to the Gini coefficient indicator,with the IMF having the largest Gini coefficient selected as the optimal component.Secondly,the SCSSA is employed to iteratively optimize the filter length L,fault signal period T,and displacement parameter M in the MCKD algorithm,determining the optimal parameter combination for MCKD.This avoids the limitations of manual settings and enhances the accuracy of fault diagnosis.The optimized MCKD is then applied to the optimal component,and deconvolution is performed using maximum correlation kurtosis as the criterion to extract fault characteristic information through its envelope spectrum.To verify the effectiveness and generalizability of the proposed method,simulations,experimental signals from the Case Western Reserve University Bearing Center,and actual measured signals from railway freight car bearing 353130B are used to analyze inner ring faults.The experimental results demonstrate that the method can accurately extract fault characteristic information of railway freight car bearings under noise interference and identify the fault type.展开更多
传统的货车运行故障动态图像检测系统(trouble of moving freight car detection system,TFDS)通过图像采集加人工判读的方式完成车辆状态检查和分析,费时费力。近年来,随着人工智能的发展,TFDS系统中逐渐加入智能识别算法,但受限于样...传统的货车运行故障动态图像检测系统(trouble of moving freight car detection system,TFDS)通过图像采集加人工判读的方式完成车辆状态检查和分析,费时费力。近年来,随着人工智能的发展,TFDS系统中逐渐加入智能识别算法,但受限于样本量少、环境复杂等因素,智能识别算法的识别准确率仍不能满足工程应用要求。为此,文中提出一种基于反馈修正弱光增强的运煤火车外观状态智能检测识别方法,实现高效高精度智能识别车辆外观状态。首先,为解决户外环境光线不断变化带来的弱光图像质量影响智能识别算法准确率的问题,比较研究了六种弱光增强算法对原始图像的预处理性能及其对火车车厢目标识别准确率的影响。结果表明:应用URetinex-Net方法增强后,火车车厢目标识别准确率可以从55%提升到90%。另外,为了解决车辆异常状态的样本数据量有限带来的火车车辆外观状态检测识别与建模过程中严重的数据不均衡问题,文中提出通过多次迭代训练加反馈修正的方式不断提高目标检测模型的准确率,可将识别准确率提升到95.2%。目前该系统已部署于某铁路运煤区间站点并平稳运行,提高了工作效率,具有较高的推广和应用价值。展开更多
基金supported by Research and Development Plan of China Railway Group(N2023J065).
文摘Purpose-Weathering steel has excellent resistance to atmospheric corrosion,but still faces complex environmental corrosion problems during long-term operation.This paper mainly studies the corrosion problem of weather resistant steel materials for railway freight car bodies with a load capacity of 70 tons.Design/methodology/approach-The paper analyzes the corrosion characteristics of weather resistant steel materials for truck bodies through macroscopic and microscopic methods including metallographic microscopy,scanning electron microscopy,energy dispersive spectroscopy and X-ray diffraction.Electrochemical analysis shows that the rust layer on the surface of weathering steel changes the surface state of the material,and also proves that weathering steel used in trucks undergoes electrochemical corrosion under atmospheric corrosion.At the same time,ion chromatography technology is used to study the corrosive ions mainly present in the residual liquid and foam solution inside the vehicle body.Findings-The corrosion of truck body materials is mainly electrochemical corrosion,and the corrosion of door materials is more obvious than that of other parts.The corrosion products are mainly Fe oxides and hydroxides.There are high concentrations of Cl-and SO42-ions in the residual liquid and foam solution at the bottom of the freight car,which are the main factors causing corrosion of the railway freight car body.Originality/value-The foam adhesive around the door panel is in a moist state for a long time,and corrosive ions will accelerate the electrochemical corrosion of the weather resistant steel material of the door panel.Therefore,the corrosion of the cargo door panel is more severe than other components.
文摘To address the issue of accurately extracting fault characteristic information of railway freight car bearings under noisy conditions,this paper proposes a fault diagnosis method based on Adaptive Chirp Mode Decomposition(ACMD)and an optimized Maximum Correlation Kurtosis Deconvolution(MCKD)using a Sparrow Search Algorithm Combining Sine-Cosine and Cauchy Mutation(SCSSA).Firstly,ACMD is used to decompose and reconstruct the original fault signal to obtain several Intrinsic Mode Functions(IMFs).Then,the IMFs are filtered according to the Gini coefficient indicator,with the IMF having the largest Gini coefficient selected as the optimal component.Secondly,the SCSSA is employed to iteratively optimize the filter length L,fault signal period T,and displacement parameter M in the MCKD algorithm,determining the optimal parameter combination for MCKD.This avoids the limitations of manual settings and enhances the accuracy of fault diagnosis.The optimized MCKD is then applied to the optimal component,and deconvolution is performed using maximum correlation kurtosis as the criterion to extract fault characteristic information through its envelope spectrum.To verify the effectiveness and generalizability of the proposed method,simulations,experimental signals from the Case Western Reserve University Bearing Center,and actual measured signals from railway freight car bearing 353130B are used to analyze inner ring faults.The experimental results demonstrate that the method can accurately extract fault characteristic information of railway freight car bearings under noise interference and identify the fault type.
文摘传统的货车运行故障动态图像检测系统(trouble of moving freight car detection system,TFDS)通过图像采集加人工判读的方式完成车辆状态检查和分析,费时费力。近年来,随着人工智能的发展,TFDS系统中逐渐加入智能识别算法,但受限于样本量少、环境复杂等因素,智能识别算法的识别准确率仍不能满足工程应用要求。为此,文中提出一种基于反馈修正弱光增强的运煤火车外观状态智能检测识别方法,实现高效高精度智能识别车辆外观状态。首先,为解决户外环境光线不断变化带来的弱光图像质量影响智能识别算法准确率的问题,比较研究了六种弱光增强算法对原始图像的预处理性能及其对火车车厢目标识别准确率的影响。结果表明:应用URetinex-Net方法增强后,火车车厢目标识别准确率可以从55%提升到90%。另外,为了解决车辆异常状态的样本数据量有限带来的火车车辆外观状态检测识别与建模过程中严重的数据不均衡问题,文中提出通过多次迭代训练加反馈修正的方式不断提高目标检测模型的准确率,可将识别准确率提升到95.2%。目前该系统已部署于某铁路运煤区间站点并平稳运行,提高了工作效率,具有较高的推广和应用价值。
