A multivariate method for fault diagnosis and process monitoring is proposed. This technique is based on a statistical pattern(SP) framework integrated with a self-organizing map(SOM). An SP-based SOM is used as a cla...A multivariate method for fault diagnosis and process monitoring is proposed. This technique is based on a statistical pattern(SP) framework integrated with a self-organizing map(SOM). An SP-based SOM is used as a classifier to distinguish various states on the output map, which can visually monitor abnormal states. A case study of the Tennessee Eastman(TE) process is presented to demonstrate the fault diagnosis and process monitoring performance of the proposed method. Results show that the SP-based SOM method is a visual tool for real-time monitoring and fault diagnosis that can be used in complex chemical processes.Compared with other SOM-based methods, the proposed method can more efficiently monitor and diagnose faults.展开更多
Tubular hydroforming has attracted increased attention in the vehicle industry recently. This paper covers a complete hydroforming process design for an instrum ent panel frame by finite element simulation using the e...Tubular hydroforming has attracted increased attention in the vehicle industry recently. This paper covers a complete hydroforming process design for an instrum ent panel frame by finite element simulation using the explicit code LS-DYNA. The manufacturing process for the instrument panel frame consists of tube pre-be nding and final hydroforming. To accomplish hydroforming process design successf ully, a thorough investigation of proper combination of process parameters such as internal hydraulic pressure and axial feeding is carried out by finite element simulation to predict the tube wall thickness and shape. An optimized process parameter combination is obtained and verified by the instrument panel frame hyd roforming experiment. The experiment shows that designed process parameters can be used in real production through FEA simulation, but tubular thinned amplitu de by FEA is less than that with the experiment.展开更多
基金Project(2013CB733605)supported by the National Basic Research Program of ChinaProject(21176073)supported by the National Natural Science Foundation of ChinaProject supported by the Fundamental Research Funds for the Central Universities,China
文摘A multivariate method for fault diagnosis and process monitoring is proposed. This technique is based on a statistical pattern(SP) framework integrated with a self-organizing map(SOM). An SP-based SOM is used as a classifier to distinguish various states on the output map, which can visually monitor abnormal states. A case study of the Tennessee Eastman(TE) process is presented to demonstrate the fault diagnosis and process monitoring performance of the proposed method. Results show that the SP-based SOM method is a visual tool for real-time monitoring and fault diagnosis that can be used in complex chemical processes.Compared with other SOM-based methods, the proposed method can more efficiently monitor and diagnose faults.
文摘Tubular hydroforming has attracted increased attention in the vehicle industry recently. This paper covers a complete hydroforming process design for an instrum ent panel frame by finite element simulation using the explicit code LS-DYNA. The manufacturing process for the instrument panel frame consists of tube pre-be nding and final hydroforming. To accomplish hydroforming process design successf ully, a thorough investigation of proper combination of process parameters such as internal hydraulic pressure and axial feeding is carried out by finite element simulation to predict the tube wall thickness and shape. An optimized process parameter combination is obtained and verified by the instrument panel frame hyd roforming experiment. The experiment shows that designed process parameters can be used in real production through FEA simulation, but tubular thinned amplitu de by FEA is less than that with the experiment.
