Intelligent Diagnosis and Prognosis of Tool Wear Using Dominant Feature Identification

Identification and prediction of a lifetime of industrial cutting tools using minimal sensors is crucial to reduce production costs and downtime in engineering systems. In this paper, we provide a formal decision software tool to extract the dominant features enabling tool wear prediction. This decision tool is based on a formal mathematical approach that selects dominant features using the singular value decomposition of real-time measurements from the sensors of an industrial cutting tool. Selection of dominant features is important, as retaining only essential features allows reduced signal processing or even reduction in the number of required sensors, which cuts costs. It is shown that the proposed method of dominant feature selection is optimal in the sense that it minimizes the least-squares estimation error. The identified dominant features are used with the recursive least squares (RLS) algorithm to identify parameters in forecasting the time series of cutting tool wear. Experimental results on an industrial high-speed milling machine show the effectiveness in predicting the tool wear using only the dominant features.      

激光切割质量的在线评价方法

在工艺实验的基础上,建立了切割面分层理论模型.实验研究和模型分析均表明:切割面近下缘处是切割质量的最薄弱环节,此处粗糙度最高,切割前沿在下缘处的温度是决定下缘质量的主要因素.提出以近下缘粗糙度作为切割质量评价和检测的主要指标,建立了火花簇射的视觉检测系统,从侧面研究了切割过程中的火花簇射行为,发现火花簇射视觉图像特征与切割速度以及切割面近下缘粗糙度之间具有良好的对应关系:随着切割速度的变化,最高的火花簇射出口温度(亮度)对应于最低的切割面近下缘粗糙度,此时的切割速度为该工艺条件下的最佳切割速度,从而实现了对切割面下缘质量的在线检测.     

在线铁谱图像分析中基才蚁群算法改进Otsu的设计与应用

在线铁谱图像获取机器磨损状态信息是铁谱诊断技术的核心和瓶颈。针对在线铁谱磨粒图像的Kirsch边缘检测特征不明显和Otsu（最大类间方差法）获取最佳阈值的局限性及耗时等问题,设计了一种基于蚁群算法改进Otsu方法完成图像分割,并结合Kirsch边缘检测来提取磨粒图像信息的新方法。首先通过Kirsch算子检测出图像边缘．然后运用基于蚁群算法改进Otsu方法求取最佳阈值并进行二值化处理．最后采用灰度堆栈空间实现磨粒自动定位。通过现场对三峡电厂5号水轮发电机组2012年油液进行试验和数据分析、及近一年的机组开机老化运行．得出所设计的算法能够有效提取磨粒图像信息,同时节省运算时间,对水轮机组故障预测、诊断起到了良好的实际作用。     

PCBN刀具激光超声复合切削硬质合金的磨损机理

结合激光加热辅助切削和超声振动切削提出了激光超声复合切削加工工艺。采用PCBN刀具对YG10硬质合金进行普通切削、超声振动切削、激光加热辅助切削和激光超声复合切削对比试验,采用超景深显微镜观测刀具磨损量及磨损形貌,通过扫描电子显微镜（SEM）对刀具磨损区域进行能谱分析,研究激光超声复合切削条件下刀具的磨损规律、磨损形态及磨损原因。研究结果表明:与普通切削、超声振动切削及激光加热辅助切削相比,激光超声复合切削时刀具后刀面磨损量平均值分别降低57.5%、46%、41.3%,刀具使用寿命明显提高;刀具磨损形态主要表现为前刀面磨损、后刀面磨损和崩刃;激光超声复合切削硬质合金时粘接磨损、氧化磨损、相变磨损和微裂解磨损是引起PCBN刀具磨损的主要原因。     

Current-sensor-based feed cutting force intelligent estimation andtool wear condition monitoring

Tool wear condition monitoring has the potential to play a critical role in ensuring the dimensional accuracy of the workpiece and prevention of damage to cutting equipment. It could also help in automating cutting processes. In this paper, the feed cutting force estimated with the aid of an inexpensive current sensor installed on the AC servomotor of a computerized numerical control tuning center is used to monitor tool wear condition. To achieve this, the feed drive system is modeled, using neuro-fuzzy techniques, to provide the framework for estimating the feed cutting force based on the feed motor current measured. Functional dependence of the feed cutting force on tool wear and cutting parameters are then expressed in the form of a difference equation relating variation in the feed cutting force to tool wear rate. The computerized system automatically compares successive feed cutting force estimates and determines the onset of accelerated tool wear in order to issue a request for tool replacement. Experimental results show that the tool wear condition monitoring is effective and industrially applicable     

同质背景预测用于红外弱小目标检测

背景预测是红外弱小目标检测中抑制背景的主要方法之一.提出了一种同质背景预测算法,在分析空背景下不同背景成分图像灰度特征模型的基础上,首先对图像进行边缘检测,将图像划分为不同灰度性质的区域,然后使用边缘检测结果调制预测权值矩阵.仿真结果表明,该算法对背景杂波具有很好的抑制效果,能够有效保护图像细节,明显降低异质区域像素灰度对预测的不利影响,显著改善低信噪比条件下弱小目标的检测性能.     

边缘网络中一种VNF需求预测方法

针对当前虚拟网络功能（Virtualization Network Functions,VNF）需求预测方法准确率较低且不适用于边缘网络的问题,提出了一种在边缘网络中基于支持向量回归（Support Vector Regression,SVR）与门控循环单元（Gated Recurrent Unit,GRU）神经网络模型结合的VNF需求预测方法。考虑到网络边缘流量具有突发性、自相似性及长相关性等特点,结合SVR和GRU两种模型的优点,利用计算复杂度较低的SVR和GRU模型分别提取网络服务历史时序数据的短期特征和长期特征,以提高VNF需求预测准确率,实现边缘网络中VNF的提前放置。实验表明,所提出的预测方法在边缘网络中针对不同网络服务的预测较于传统方法、循环神经网络（Recurrent Neural Networks,RNN）、长短期记忆网络（Long Short-Term Memory,LSTM）模型能够降低20%~30%的误差,有更佳的预测效果。     

强噪声背景下在遥感云图中提取地球圆盘的快速算法

提出一种新的图像边缘提取的快速算法——通过建立马尔可夫预测模型对目标边缘位置进行前向预测，并根据边缘特性，采用最小均方误差分类器进行同步校正，与传统的边缘提取算法相比，该算法具有很强的噪声抑制和实时处理能力，实践表明，该算法对于任何非突变闭合区域均有良好的边缘跟踪特性，已成功应用于航天遥感图像的实时采集和处理系统中。     

Prediction of sawing force for single-crystal silicon carbide with fixed abrasive diamond wire saw

Fixed abrasive diamond wire saw has been used to cut hard-and-brittle materials into wafers, such as silicon carbide. The force of a single abrasive determines the cutting depth, and affects material removal mode and crack propagation length. Therefore, the sawing force is a key factor that affects the surface/subsurface quality of wafers. In this paper, a numerical sawing force predicting method considering wire saw parameters was proposed with the combination of both ductile removal and brittle fracture removal for each single abrasive. A new calculation method of single abrasive cutting force considering frictional force component and new material removal way considering the effect of lateral crack were adopted. Then the influences of process parameters and wire parameters on sawing force were analyzed. Finally, mathematical sawing force formulas described by both process parameters and wire saw parameters were obtained using the new sawing force prediction method. The validity of this prediction method and sawing force formulas was verified through experiments in the literature under the same process parameters and wire saw parameters.     

一种基于背景预测的红外弱小目标检测方法

介绍了一种新的基于背景预测的空中红外弱小目标检测方法,以提高对复杂背景预测的准确性,减小云层边缘预测不准确形成的虚警.该方法对云层边缘处的点根据其不同尺度邻域上的亮暗点分布特点进行预测;对非边缘点采用基本背景预测法进行预测,最后经过背景对消,将弱小目标检测出来.实验结果表明,与已报导的其它方法比较,该方法能够更有效地抑制云层边缘引起的虚警.     

一种基于突发长度预测的光突发汇聚机制

提出了一种基于突发长度预测的固定时间汇聚方法.边缘节点在监测时间段内对到达的数据流进行监测,并且根据监测的结果预测在固定的汇聚时间内完成汇聚的突发包长度,提前将控制分组转发到核心网络中进行资源预留.通过理论分析及计算机仿真表明,这种汇聚方法能够有效地降低光突发交换网络中的端到端延迟.     

基于视觉激光切割厚板切割状态监控方法

利用光纤镜头和彩色工业摄像机实时采集激光切割厚板中切割点的图像,从彩色图像中分别选取蓝色、绿色和红色通道图像,分析各通道图像的特点和切割点的几何形状特征。首先以激光焦点在图像中的位置为中心建立坐标系,以x轴方向为起始,45°为间隔向8个方向搜索激光切割区域的边缘点,根据边缘点到坐标原点的距离信息确定激光切割方向和切割顶点;建立边缘识别用抛物线模型,根据边缘处存在灰度特征、梯度特征和方向特征设计识别目标函数,识别切割顶点两侧边缘,进而识别整个切割点处的几何形状。实验表明识别方法具有良好的适应性、准确性和实时性。     

原子量级条件下单晶硅磨削过程中的亚表面损伤

应用分子动力学仿真研究了原子量级条件下磨粒钝圆半径、磨削深度和磨削速度对单晶硅磨削后亚表面损伤层深度的影响.分子动力学仿真结果表明:在磨削深度和磨削速度相同情况下,随着磨粒钝圆半径的减小,损伤层深度和硅原子间势能亦减小.随着磨削深度的增大,损伤层深度和硅原子间势能增大.在磨削深度和磨粒钝圆半径相同的情况下,在20～200 m/s范围内,磨削速度对单晶硅亚表面损伤影响很小,说明分子动力学仿真对磨削速度的变化不敏感,因此可以适当提高仿真速度,从而缩短仿真时间和扩大仿真规模.单晶硅亚表面损伤主要是基于硅原子间势能的变化,并通过超精密磨削实验进行了实验验证.     

原子量级条件下单晶硅磨削过程中的亚表面损伤

应用分子动力学仿真研究了原子量级条件下磨粒钝圆半径、磨削深度和磨削速度对单晶硅磨削后亚表面损伤层深度的影响.分子动力学仿真结果表明:在磨削深度和磨削速度相同情况下,随着磨粒钝圆半径的减小,损伤层深度和硅原子间势能亦减小.随着磨削深度的增大,损伤层深度和硅原子间势能增大.在磨削深度和磨粒钝圆半径相同的情况下,在20～200 m/s范围内,磨削速度对单晶硅亚表面损伤影响很小,说明分子动力学仿真对磨削速度的变化不敏感,因此可以适当提高仿真速度,从而缩短仿真时间和扩大仿真规模.单晶硅亚表面损伤主要是基于硅原子间势能的变化,并通过超精密磨削实验进行了实验验证.     

微区熔化法激光切削

提出一种应用激光切削加工的新途径:将激光束会聚成光带,用以加热、熔化余量和零件分界面的微区,周时用工具剥离已分离的切屑,分析和初步试验证明了这种激光切削方法的可行性。其切削力小,刀具磨损小,激光能量使用经济。     

基于神经网络的铜转炉内壁蚀损红外检测方法

针对铜转炉内壁蚀损状态难于直接检测的问题,提出了一种基于神经网络和红外无损检测技术的铜转炉内壁蚀损在线检测方法,分析了炉表面温度场与炉衬内壁蚀损的对应关系以及由红外热像仪测取炉表面温度场、图像处理与神经网络智能计算炉内壁蚀损量的检测原理,建立了相应的检测系统.试验检测的误差在5%之内,结果表明:建立的铜转炉内壁蚀损红外检测方法是可行的,具有较好的适应性,可满足现场的测量要求.     

Large finite array analysis using infinite array data

The prediction of edge element behavior is a common problem during the design of large array antennas. The performance of the center elements can be approximated by an infinite array model, but the edge element patterns and active reflection coefficients cannot. The full element-by-element analysis of a large finite array is either excessively time consuming or impossible due to the computer power required. A study has recently been carried out to develop and test methods of fully predicting large array performance using infinite array data. The methods devised are presented, together with comparisons of predicted performance and measured data from a 163-element WG-16 array     

皮秒激光旋切加工微孔试验研究

为了解决毫/纳秒激光加工微孔质量低的问题,利用脉冲宽度为200ps的脉冲激光,采用高速旋切法对厚度为0.2mm的SUS 304不锈钢薄板进行直径为200μm的微孔加工试验,用激光共聚焦显微镜观察孔的外观形貌,研究旋切速率、激光功率和离焦量等因素对孔径、锥度和热影响区等加工质量的影响。结果表明,旋切速率对微孔内壁质量有直接的影响;通过提高转速来降低激光脉冲重叠率可以减小微孔内壁的热影响区;适当增加激光功率,能够改善旋切加工微孔切口处的加工质量;采用正离焦加工能够一定程度减小孔的锥度。优化工艺参量能够加工出热影响区小、边缘质量好的小锥度微孔。     

基于DOE优化光学玻璃晶片边缘磨削工艺

在光电器件的制造过程中,用光学玻璃晶片作为电路制作的基板材料。玻璃晶片通过在大面积的玻璃面板上划圆获得。划圆后会形成非常锐利的边缘,需要将锐利边缘磨削成圆弧形,以减少在后续加工中产生破损、崩边。在光学玻璃晶片的边缘磨削中,合适的玻璃晶片边缘磨削参数对于晶片边缘磨削后的崩边情况、磨削斜面宽度、中心误差等均有很大影响。利用DOE试验方法,光学玻璃晶片边缘磨削过程中有效减小崩边,并给出了影响因素,获得并验证了最优化的磨削工艺参数,减少了晶片磨削后的崩边破损。     

Big Data-Based Transformer Substation Fault Prediction Method

Transformer substations play a major role in power systems. The fault of a transformer substation will jeopardize the safety and effective operation of the power system. The fault signal of a transformer substation includes the fault status and fault occurrence time. In this paper, we propose a transformer substation fault prediction method based on big data analysis. Thus, a new transformer substation fault prediction method is developed by combining the advantages of decision tree algorithms and grey system theory to predict the fault status and occurrence time with high accuracy. As a case study, the transformer substation fault signals obtained from a region in the southwest of China are analyzed using the proposed method based on big data. The experimental results confirm that the proposed method achieves high-accuracy fault prediction.