Although machine learning models have achieved high enough accuracy in predicting shield position deviations,their“black box”nature makes the prediction mechanisms and decision-making processes opaque,leading to wea...Although machine learning models have achieved high enough accuracy in predicting shield position deviations,their“black box”nature makes the prediction mechanisms and decision-making processes opaque,leading to weaker explanations and practicability.This study introduces a novel explainable deep learning framework comprising the Informer model with enhanced attention mechanisms(EAMInfor)and deep learning important features(DeepLIFT),aimed at improving the prediction accuracy of shield position deviations and providing interpretability for predictive results.The EAMInfor model attempts to integrate channel attention,spatial attention,and simple attention modules to improve the Informer model's performance.The framework is tested with the four different geological conditions datasets generated from the Xiamen metro line 3,China.Results show that the EAMInfor model outperforms the traditional Informer and comparison models.The analysis with the DeepLIFT method indicates that the push thrust of push cylinder and the earth chamber pressure are the most significant features,while the stroke length of the push cylinder demonstrated lower importance.Furthermore,the variation trends in the significance of data points within input sequences exhibit substantial differences between single and composite strata.This framework not only improves predictive accuracy but also strengthens the credibility and reliability of the results.展开更多
Error modelling and compensating technology is an effective method to improve the processing precision.The position and orientation deviation of workpiece is caused by the fixing and manufacturing errors of the fixtur...Error modelling and compensating technology is an effective method to improve the processing precision.The position and orientation deviation of workpiece is caused by the fixing and manufacturing errors of the fixture.How to reduce the position and orientation deviation of workpiece has become a technical problem of improving the processing quality of workpiece.In order to increase machining accuracy,an implementation scheme of fixture system comprehensive errors（FSCE） compensation is proposed.A FSCE parameter model is established by analyzing the influence of contact points on the position and orientation of workpiece.Meanwhile,a parameter identification method for FSCE parameter model is presented by using the 3-2-1 deterministic positioning fixture,which determines the model parameters.Moreover,a FSCE compensation model is formulated to study the compensation value of the cutting position.By using RenishawOMP60 Probe and combining vertical machining centre（SKVH850） equipment with SKY2001 Open CNC System,on-machine verification system（OMVS） is built to measure FSCE successfully.The processing error can be reduced by analyzing the cutting position of the tool with the homogeneous transformation of space coordinate system.Finally,the compensation experiment of real time errors is conducted,and the cylindricality and perpendicularity errors of hole surface are reduced by 30.77% and 28.57%,respectively.This paper provides a new way of realizing the compensation of FCSE,which can improve the machining accuracy of workpiece largely.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.52378392,52408356)the Foal Eagle Program Youth Top-notch Talent Project of Fujian Province,China(Grant No.00387088).
文摘Although machine learning models have achieved high enough accuracy in predicting shield position deviations,their“black box”nature makes the prediction mechanisms and decision-making processes opaque,leading to weaker explanations and practicability.This study introduces a novel explainable deep learning framework comprising the Informer model with enhanced attention mechanisms(EAMInfor)and deep learning important features(DeepLIFT),aimed at improving the prediction accuracy of shield position deviations and providing interpretability for predictive results.The EAMInfor model attempts to integrate channel attention,spatial attention,and simple attention modules to improve the Informer model's performance.The framework is tested with the four different geological conditions datasets generated from the Xiamen metro line 3,China.Results show that the EAMInfor model outperforms the traditional Informer and comparison models.The analysis with the DeepLIFT method indicates that the push thrust of push cylinder and the earth chamber pressure are the most significant features,while the stroke length of the push cylinder demonstrated lower importance.Furthermore,the variation trends in the significance of data points within input sequences exhibit substantial differences between single and composite strata.This framework not only improves predictive accuracy but also strengthens the credibility and reliability of the results.
基金supported by National Natural Science Foundation of China (Grant No. 50975200)National Key Technologies R & D Programmer of China (Grant No. 2009ZX04014-021)
文摘Error modelling and compensating technology is an effective method to improve the processing precision.The position and orientation deviation of workpiece is caused by the fixing and manufacturing errors of the fixture.How to reduce the position and orientation deviation of workpiece has become a technical problem of improving the processing quality of workpiece.In order to increase machining accuracy,an implementation scheme of fixture system comprehensive errors（FSCE） compensation is proposed.A FSCE parameter model is established by analyzing the influence of contact points on the position and orientation of workpiece.Meanwhile,a parameter identification method for FSCE parameter model is presented by using the 3-2-1 deterministic positioning fixture,which determines the model parameters.Moreover,a FSCE compensation model is formulated to study the compensation value of the cutting position.By using RenishawOMP60 Probe and combining vertical machining centre（SKVH850） equipment with SKY2001 Open CNC System,on-machine verification system（OMVS） is built to measure FSCE successfully.The processing error can be reduced by analyzing the cutting position of the tool with the homogeneous transformation of space coordinate system.Finally,the compensation experiment of real time errors is conducted,and the cylindricality and perpendicularity errors of hole surface are reduced by 30.77% and 28.57%,respectively.This paper provides a new way of realizing the compensation of FCSE,which can improve the machining accuracy of workpiece largely.
