Bayesian networks modeling for thermal error of numerical control machine tools

The interaction between the heat source location, its intensity, thermal expansion coefficient, the machine system configuration and the running environment creates complex thermal behavior of a machine tool, and also makes thermal error prediction difficult. To address this issue, a novel prediction method for machine tool thermal error based on Bayesian networks (BNs) was presented. The method described causal relationships of factors inducing thermal deformation by graph theory and estimated the thermal error by Bayesian statistical techniques. Due to the effective combination of domain knowledge and sampled data, the BN method could adapt to the change of running state of machine, and obtain satisfactory prediction accuracy. Ex- periments on spindle thermal deformation were conducted to evaluate the modeling performance. Experimental results indicate that the BN method performs far better than the least squares (LS) analysis in terms of modeling estimation accuracy.

Patient-specific three-dimensional printed heart models benefit preoperative planning for complex congenital heart disease

Background Preoperative planning for children with congenital heart diseases remains crucial and challenging.This study aimed to investigate the roles of three-dimensional printed patient-specific heart models in the presurgical planning for complex congenital heart disease.Methods From May 2017 to January 2018,15 children diagnosed with complex congenital heart disease were included in this study.Heart models were printed based on computed tomography (CT) imaging reconstruction by a 3D printer with photosensitive resin using the stereolithography apparatus technology.Surgery options were first evaluated by a sophisticated cardiac surgery group using CT images only,and then surgical plans were also set up based on heart models.Results Fifteen 3D printed heart models were successfully generated.According to the decisions based on CT,13 cases were consistent with real options,while the other 2 were not.According to 3D printed heart models,all the 15 cases were consistent with real options.Unfortunately,one child diagnosed with complete transposition of great arteries combined with interruption of aortic arch (type A) died 5 days after operation due to postoperative low cardiac output syndrome.The cardiologists,especially the younger ones,considered that these 3D printed heart models with tangible,physical and comprehensive illustrations were beneficial for preoperative planning of complex congenital heart diseases.Conclusion 3D printed heart models are beneficial and promising in preoperative planning for complex congenital heart diseases,and are able to help conform or even improve the surgery options.

基于自适应无味卡尔曼滤波的机床选点温升快速辨识方法研究（英文）

研究目的:为了缩短机床温升试验时间,提出一种机床热特性快速辨识方法,利用较短时间的温度采样数据即可准确预测出完整的温升曲线,进而获得热平衡时间及稳态温度等热特性参数。创新要点:提出了基于自适应无味卡尔曼滤波的机床选点温升快速辨识方法,其中最短辨识时间判据可以有效解决如何寻找准确辨识热特性参数的最短采样时间问题,而自适应无味卡尔曼滤波则可以实时调整参数,防止外界因素对辨识的干扰。研究方法:由于无味卡尔曼滤波在非线性状态预测和参数辨识上具有优势,所以本文将无味卡尔曼滤波算法应用到机床选点温升辨识上。为了防止辨识过程中的发散退化等问题,将无味卡尔曼滤波发展为自适应无味卡尔曼滤波(图1)。在快速辨识方法上提出了最短辨识时间判据(图2)。文章中又将此算法应用到实际的立式加工中心温升辨识上,证明了该算法的可行性及有效性(图5和6)。最后又将带有自适应调整过程的无味卡尔曼滤波算法和不带调整过程的算法做了对比,显示了自适应调整过程对辨识算法的重要性(图6和11)。重要结论:基于自适应无味卡尔曼滤波的机床选点温升快速辨识方法可以准确快速地辨识出温升曲线,获取热特性参数,将原来394 min的热平衡试验时间缩短,只需28 min即可得到温升变化情况。

Research on transmission performance of a surface acoustic wave sensing system used in manufacturing environment monitoring

Surface acoustic wave （SAW） sensors show great promise in monitoring fast-rotating or moving machinery in manufacturing environments, and have several advantages in the measurement of temperature, torque, pressure, and strain because of their passive and wireless capability. However, very few studies have systematically attempted to evaluate the characteristics of SAW sensors in a metal environment and rotating structures, both of which are common in machine tools. Simulation of the influence of the metal using CST software and a series of experiments with an SAW temperature sensor in real environments were designed to investigate the factors that affect transmission pertbrmance, including antenna angles, orientations, rotation speeds, and a metallic plate, along with the interrogator antenna-SAW sensor antenna separation distance. Our experimental measure- ments show that the sensor＇s optimal placement in manufacturing environments should take into account all these factors in order to maintain system measurement and data transmission capability. As the first attempt to systematically investigate the transmis- sion characteristics of the SAW sensor used in manufacturing environment, this study aims to guide users of SAW sensor appli- cations and encourage more research in the field of wireless passive SAW sensors in monitoring applications.

Automated process parameters tuning for an injection moulding machine with soft computing

In injection moulding production,the tuning of the process parameters is a challenging job,which relies heavily on the experience of skilled operators.In this paper,taking into consideration operator assessment during moulding trials,a novel intelligent model for automated tuning of process parameters is proposed.This consists of case based reasoning (CBR),empirical model (EM),and fuzzy logic (FL) methods.CBR and EM are used to imitate recall and intuitive thoughts of skilled operators,respectively,while FL is adopted to simulate the skilled operator optimization thoughts.First,CBR is used to set up the initial process parameters.If CBR fails,EM is employed to calculate the initial parameters.Next,a moulding trial is performed using the initial parameters.Then FL is adopted to optimize these parameters and correct defects repeatedly until the moulded part is found to be satisfactory.Based on the above methodologies,intelligent software was developed and embedded in the controller of an injection moulding machine.Experimental results show that the intelligent software can be effectively used in practical production,and it greatly reduces the dependence on the experience of the operators.