The existing bearing temperature fault detection and early warning system has a high false alarm rate and insufficient early warning ability. For this reason, in this study, a method for detecting the abnormal bearing temperature of high-speed trains based on spatiotemporal fusion decision-making was proposed. First, the temperature characteristics of similar bearings were compared and analyzed with different spatial distributions. Then, a bearing abnormal temperature rise detection model based on the analytic hierarchy process (AHP) entropy method was proposed. Second, the temperature characteristics of the same bearings were compared and analyzed with different time distributions. A real-time prediction model of high-speed train bearing temperature anomalies based on Bi-directional Long Short-Term Memory (BILSTM) was proposed. Finally, the D-S evidence theory was used to combine the anomaly detection model based on the AHP entropy method and the anomaly detection model based on BILSTM real-time prediction. Through the comprehensive diagnosis and decision-making of high-speed train bearings from two dimensions of space and time, a more comprehensive and accurate anomaly detection model was realized. The experimental results showed that the spatiotemporal comparison fusion decision model successfully eliminated the misjudgment phenomenon of single-dimension model diagnosis and that it has good early warning ability.
An object-oriented modeling method was proposed to develop a simulation software package named GVDS which could be used to predict some aspects of dynamic behavior of railway vehicle. The package based on multi-body dynamics mainly consists of three parts, an interactive pre-processor, the solver and an interactive post-processor. With UML, demands and structure of the software package are represented. By modeling of the geometry and behavior of each object, virtual prototype of railway vehicle is formed and by the simulation, the critical speed of hunting stability, wheel-rail contact forces and so on can be determined and the hunting stability, curving behavior and ride comfort can be analyzed and evaluated. Finally, some cases are simulated. The simulation results show the effectiveness of the proposed method.
Surface roughness is strongly affected by machining parameters. In the past few decades, many researchers have established the relationship between the surface roughness and machining parameters, but less attention has been paid to tool shape and geometry. In addition, the number of tool flutes was ignored, which affects in vibrations and machining system. Therefore, this study first-time includes the tool flutes in addition to cutting speed, depth of cut and feed rate as independent variables. Firstly, a set of machining experiments were conducted using AA6061 as a work piece material to provide original data. Response Surface Model (RSM) adopted to establish the relationship model of surface roughness and machining parameters using Minitab 16. Based on analysis of variance (ANOVA), the results show cutter flutes has higher significant followed by feed rate, depth of cut and cutting speed which has less significant. Finally, machining parameters were optimized to desired surface roughness, and optimization prediction error has limited values between-0.02 and 0.02μm.
According to the requirements of high-speed machining, the feed rate control algorithm based on the acceleration-deceleration control and dynamics conditions is proposed. This algorithm not only satisfies the continuity of displacement, feed rate, acceleration and jerk of the feed movement, but also meets the dynamics condition of high-speed machining. Furthermore, the algorithm is applied to NURBS curve interpolation and optimizes the acceleration-deceleration intervals. At last, the algorithm is verified by simulation. This interpolation algorithm of feed rate control reduces the impact, machine vibration of feed, and improves the surface accuracy and quality of high-speed machining.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.