Accurate wheel-rail force data serves as the cornerstone for analyzing the wheel-rail relationship.However,achieving continuous and precise measurement of this force remains a significant challenge in the field.This a...Accurate wheel-rail force data serves as the cornerstone for analyzing the wheel-rail relationship.However,achieving continuous and precise measurement of this force remains a significant challenge in the field.This article introduces a calibration algorithm for the wheel-rail force that leverages graph neural networks and long short-term memory networks.Initially,a comprehensive wheel-rail force detection system for trains was constructed,encompassing two key components:an instrumented wheelset and a ground wheel-rail force measuring system.Subsequently,utilizing this system,two distinct datasets were acquired from the track inspection vehicle:instrumented wheelset data and ground wheel-rail force data,a feedforward neural network was employed to calibrate the instrumented wheelset data,referencing the ground wheel-rail force data.Furthermore,ground wheel-rail force data for the locomotive was obtained for the corresponding road section.This data was then integrated with the calibrated instrumented wheelset data from the track inspection vehicle.Leveraging the GNN-LSTM network,the article establishes a mapping relationship model between the wheel-rail force of the track inspection vehicle and the locomotive wheel-rail force.This model facilitates continuous measurement of locomotive wheel-rail forces across three typical scenarios:straight sections,long and steep downhill sections,and small curve radius sections.展开更多
Owing to a lack of gaugemeter and the variety of steel grades and standards in some plate mills, the longand short-term self-learning models of rolling force based on gauge soft-measuring with high precision were brou...Owing to a lack of gaugemeter and the variety of steel grades and standards in some plate mills, the longand short-term self-learning models of rolling force based on gauge soft-measuring with high precision were brought up. The soft-measuring method and target value locked method were used in these models to confirm the actual exit gauge of passes, and thick layer division and exponential smoothing method were used to dispose the deformation resistance parameter, which could be calculated from the actual data of the rolling process. The correlative mathematical methods can also be adapted to self-learning with gaugemeter. The models were applied to the process control system of AGC （automatic gauge control） reconstruction on 2800 mm finishing mill of Anyang steel and favorable effect was obtained.展开更多
基金supported by the National Key R&D Program of China(Grant No.2021YFF0501101)the National Natural Science Foundation of China(Grant Nos.62173137,62303178)the Project of Hunan Provincial Department of Education of China(Grant Nos.23A0426,22B0577).
文摘Accurate wheel-rail force data serves as the cornerstone for analyzing the wheel-rail relationship.However,achieving continuous and precise measurement of this force remains a significant challenge in the field.This article introduces a calibration algorithm for the wheel-rail force that leverages graph neural networks and long short-term memory networks.Initially,a comprehensive wheel-rail force detection system for trains was constructed,encompassing two key components:an instrumented wheelset and a ground wheel-rail force measuring system.Subsequently,utilizing this system,two distinct datasets were acquired from the track inspection vehicle:instrumented wheelset data and ground wheel-rail force data,a feedforward neural network was employed to calibrate the instrumented wheelset data,referencing the ground wheel-rail force data.Furthermore,ground wheel-rail force data for the locomotive was obtained for the corresponding road section.This data was then integrated with the calibrated instrumented wheelset data from the track inspection vehicle.Leveraging the GNN-LSTM network,the article establishes a mapping relationship model between the wheel-rail force of the track inspection vehicle and the locomotive wheel-rail force.This model facilitates continuous measurement of locomotive wheel-rail forces across three typical scenarios:straight sections,long and steep downhill sections,and small curve radius sections.
基金Item Sponsored by National Natural Science Foundation of China (50604006)
文摘Owing to a lack of gaugemeter and the variety of steel grades and standards in some plate mills, the longand short-term self-learning models of rolling force based on gauge soft-measuring with high precision were brought up. The soft-measuring method and target value locked method were used in these models to confirm the actual exit gauge of passes, and thick layer division and exponential smoothing method were used to dispose the deformation resistance parameter, which could be calculated from the actual data of the rolling process. The correlative mathematical methods can also be adapted to self-learning with gaugemeter. The models were applied to the process control system of AGC （automatic gauge control） reconstruction on 2800 mm finishing mill of Anyang steel and favorable effect was obtained.
