A model-based approach for monitoring of shape deviations in peripheral milling

This paper presents a model-based approach for monitoring of shape deviations for milling operations. In order to detect occurring shape deviations of the machined workpiece during the milling process, different kinds of process models are presented and discussed for their application on manufacturing quality monitoring. Thereby, a model-based system was presented for the monitoring of shape deviations based on measured cutting forces. For the transformation of cutting forces into shape deviations, a tool deflection model and material removal model were designed and applied to a monitoring system. The presented model-based monitoring approach delivers accurate quality information, like geometric shape deviations, which can be monitored against geometric tolerances, providing a quality monitoring of manufacturing processes. The reconstruction of shape deviations from measured cutting forces is verified experimentally by comparing measured and reconstructed shape contours.     

An in-depth study of tool wear monitoring technique based on image segmentation and texture analysis

We present a new micro-vision system for tool wear monitoring, which is essential for intelligent manufacturing. The tool wear area is divided into regions by a watershed transform, then subjected to automatic focusing and segmentation. The individual pixel gray values in each region are then replaced with the corresponding regional mean gray value. A hill climbing algorithm based on the sum modified laplacian (SML) focusing evaluation function is used to search the focal plane. In addition, we implement an adaptive Markov Random Field (MRF) algorithm to segment each region of tool wear. For our MRF model, the connection parameter value is adaptively determined by the connection degree between regions, which improves image acquisition of more integral tool wear areas. Our findings suggest that automatic focusing and segmentation of the tool wear area by region (within the tool wear area) enhance accuracy and robustness, and allow for real time acquisition of tool wear images. We also implement a complementary tool wear assessment procedure based on the surface texture of the workpiece. The optimal texture analysis window is determined using the entropy metric – a texture feature generated using a Gray Level Co-occurrence Matrix (GLCM). In the best texture analysis window, entropy remains monotonic as tool wear increases, demonstrating that entropy can be used effectively to monitor tool wear. Information from combined measurements of tool wear and workpiece texture can reliably be used to monitor tool wear conditions and improve monitoring success rates.     

基于主轴电流信号多特征融合的刀具磨损状态监测

为实现在正常生产条件下进行刀具磨损的长期在线监测,提出了基于主轴电流信号和粒子群优化支持向量机模型(PSO-SVM)的刀具磨损状态间接监测方法.首先对数控机床主轴电机电流信号进行分析,将与刀具磨损相关的主轴电流信号多个特征参数和EMD能量熵进行特征融合作为输入特征向量;其次,通过粒子群寻优算法(PSO)对支持向量机模型...     

特征分区的不确定性及模糊熵评判研究

分析了影响有效监控的各因素，阐述了刀具破损监测中存在的特征分区问题。以各个信号特征区间为模糊子集，以模糊熵值为参数来评判各种分区方法，结果表明，采用模糊熵值小的分区法能更准确识别刀具状态。     

Structural–energetic approach to the wear and diagnostics of hard-alloy tools

By multifractal parameterization of the contact surfaces of the tool and the supporting surface of the chip in the cutting process, the relation of the fractal dimensionality with the tool’s wear rate and the informational entropy is established. In addition, the nonlinear dependence of the tool life on the cutting speed is found. A diagnostic system for monitoring the dynamic stability of the cutting system and the tool wear is proposed.     

动态迁移和椒盐变异融合生物地理学优化算法的高维多阈值分割

针对高维多阈值图像分割中存在的多阈值搜索问题,提出了一种动态迁移和椒盐变异融合的生物地理学优化算法(BBOD)。首先,构建了一种基于动态扰动的迁移算子,对候选解中没有发生迁移操作的特征值添加一个动态的扰动因子,使种群的多样性增加,从而提高全局搜索能力;然后,创建了新型的变异算子,对待变异的特征值产生一个椒盐扰动,使该值在小范围内浮动,以便提高局部搜索能力和算法的收敛速度;最后,将该算法应用到基于最小交叉熵的图像高维多阈值分割中。高维多阈值分割实验结果表明,本文提出的BBOD算法能够获得最优的阈值向量,运行速度、性能指标均优于标准的生物地理学优化(BBO)算法,基于变异的生物地理学优化(BBOM)算法、FFA(Firefly Algorithm)和CSA(Cuckoo Search Algorithm),运行速度是FFA的5倍以上。该算法更适用于基于最小交叉熵的高维多阈值优化选择。     

Model-based identification of tool runout in end milling and estimation of surface roughness from measured cutting forces

This paper presents a model-based approach for the identification of tool runout and the estimation of surface roughness from measured cutting forces. In the first part of the paper, the effect of tool runout on variations in the cutting forces and the effect on surface roughness generation are studied. Thereby, several influencing parameters are identified and examined systematically. Based on theoretical considerations, systematic relationships between tool runout, resultant process force variations, and surface roughness characteristics are deduced. The sensitivity of process force variation is investigated for varying runout parameters by experimental tests. In the next part, the model-based runout identification method is developed, which identifies runout parameters accurately from the measured process forces. The approach has been tested extensively and was verified by measured runout parameters and the correlation of surface roughness characteristics of the machined workpiece. The performance of the developed approach is demonstrated in the final part by comparing the result of the model-based surface reconstruction with the measured surface topography.     

Condition monitoring studies on spindle bearing of a lathe

In modern industry, machinery must become increasingly flexible and automatic. In order to increase productivity, enhance quality and reduce cost, machine tools have to work free of any failure. When a failure occurs in a machine tool, it is necessary to identify the causes as early as possible. Machine tool condition monitoring is very important to achieve this goal. Condition monitoring is generally used on the critical subsystem of any machine tool. This paper endeavors to focus on the condition monitoring aspects on the machine tool element. In the present study, a critical subsystem has been identified based on the failure data analysis. Condition monitoring techniques like vibration monitoring, acoustic emission, Shock Pulse Method (SPM) and surface roughness have been successfully used for fault identification.     

基于监控视频的异常事件识别

提出了一种基于监控视频的异常事件识别模型,该模型可以实时监测视频中的前景目标,并通过分析目标的运动信息判断是否有异常事件的发生。首先,采用背景建模的混合高斯算法提取前景目标;然后,用金字塔迭代的L-K特征点跟踪算法得到前景的光流运动信息,并通过分析前景的面积比例、速度方差、整体熵判断视频中是否有异常事件的发生;最后,利用爆炸、人群短时聚集和分散两种异常事件做仿真实验。结果表明,该模型可以准确提取前景目标区域,并可以快速、精准地判断监控视频中的异常事件,可以为管理部门及时发现和控制异常事件提供有效的帮助。     

Condition monitoring studies on spindle bearing of a lathe

In modern industry, machinery must become increasingly flexible and automatic. In order to increase productivity, enhance quality and reduce cost, machine tools have to work free of any failure. When a failure occurs in a machine tool, it is necessary to identify the causes as early as possible. Machine tool condition monitoring is very important to achieve this goal. Condition monitoring is generally used on the critical subsystem of any machine tool. This paper endeavors to focus on the condition monitoring aspects on the machine tool element. In the present study, a critical subsystem has been identified based on the failure data analysis. Condition monitoring techniques like vibration monitoring, acoustic emission, Shock Pulse Method (SPM) and surface roughness have been successfully used for fault identification.     

基于排列熵的泵站压力管道运行状态监测

为实现泵站管道工作状态的在线监测,保障其安全稳定运行,提出一种基于排列熵算法(permutation entropy,简称PE)的泵站压力管道监测方法。该方法充分发挥排列熵算法计算简单和敏感度高等优点,适宜于处理非线性、非平稳信号,通过在关键部位设置传感器获取泵站管道的振动信号,利用信号子序列熵值的变化判断泵站管道振动状况。将该方法应用于景电工程二期七泵站管道的运行监测,通过设置不同的运行工况进行实例验证。结果表明,在开关机组瞬间,振动信号子序列熵值的最大幅差达到0.37,机组稳定运行期间子序列熵值的最大幅差仅为0.07,根据其熵值的变化可快速方便地识别出泵站管道的运行状态,具有较高的精度与可靠度。该方法为泵站管道运行状况的在线监测提供了新思路,为结构下一步安全诊断工作提供基础,具有较好的工程实用性和推广价值。     

多传感器图像融合的客观评价与分析

图像融合作为一种有效的信息融合技术，已经广泛用于军事、遥感、机器视觉和医疗诊断等领域。这里研究了多传感器图像融合效果的客观评价方法，其中包括均方根误差、平均误差、灰度标准差、熵、熵差、交叉熵、互信息和空间频率。将加权平均、金字塔、小波变换三种方法用于多传感器图像的融合，实验结果表明客观评价结果与视觉评价的结果是一致的，是一种行之有效的评价手段。     

基于熵理论和BP神经网络的船舶柴油机磨损故障识别

磨损监测与故障诊断是保证船舶柴油机安全可靠运行的重要技术手段。随着船舶柴油机运行可靠性的要求增高,其磨损监测需要更加全面,数据呈高维化,无关数据和冗余数据增多,使故障诊断的复杂程度增大,且近年来,船舶柴油机故障诊断的智能化需求日益增高。针对以上问题和需求,基于信息熵理论,应用信息熵值与度量熵组合设计柴油机磨损监测与故障诊断特征属性约简算法,将某型柴油机润滑磨损故障诊断特征指标维度从16维降低至7维;应用设计的BP神经网络和磨损故障模式识别规则,以该型柴油机44个磨损故障诊断数据样本为对象,进行应用验证与研究分析。结果表明,构建的模型在保证数据集分类特性的基础上,有效实现其数据降维,且所构建的磨损故障识别BP神经网络在属性约简后,故障识别的准确性有明显提高。     

Detection of broken rotor bars in induction motors using nonlinear Kalman filters

This paper presents a model-based fault detection approach for induction motors. A new filtering technique using Unscented Kalman Filter (UKF) and Extended Kalman Filter (EKF) is utilized as a state estimation tool for on-line detection of broken bars in induction motors based on rotor parameter value estimation from stator current and voltage processing. The hypothesis on which the detection is based is that the failure events are detected by jumps in the estimated parameter values of the model. Both UKF and EKF are used to estimate the value of rotor resistance. Upon breaking a bar the estimated rotor resistance is increased instantly, thus providing two values of resistance after and before bar breakage. In order to compare the estimation performance of the EKF and UKF, both observers are designed for the same motor model and run with the same covariance matrices under the same conditions. Computer simulations are carried out for a squirrel cage induction motor. The results show the superiority of UKF over EKF in nonlinear system (such as induction motors) as it provides better estimates for rotor fault detection.     

基于小波包能谱熵的铣削颤振监测方法

针对切削加工过程中容易出现颤振,导致零件表面加工质量降低,本文以铣削加工为研究对象,提出了基于小波包能谱熵的铣削颤振监测方法。信号的采集是一个连续的过程,为避免刀具不参与切削对这种方法的影响,本文提出基于铣削力幅值平方和的方法以识别刀具是否参与切削。试验结果表明,无论对于刀具是否参与切削的识别或者是否出现铣削颤振的监测都能有效的监测。     

Process fault isolation based on transfer entropy algorithm

Complexity of industrial plants and their stringent environmental and safety regulations have necessitated early detection and isolation of process faults. All the existing fault isolation methods can be categorized into two general groups: model-based and data-based. Transfer entropy is a data-based method for measuring propagation direction of disturbance and finding its root cause. In this paper, a new transfer entropy-based method is proposed to isolate different process faults. The novelty of this paper lies in using the transfer entropy idea to generate distinct patterns of information flow among process variables, recognize their correlations in the context of the transferred information in any abnormal condition, and finally isolate different process faults. The experimental results clearly demonstrate the superiority of the proposed method to the conventional methods.     

On-machine tool prediction of flank wear from machined surface images using texture analyses and support vector regression

In this paper, a method for on-machine tool condition monitoring by processing the turned surface images has been proposed. Progressive monitoring of cutting tool condition is inevitable to maintain product quality. Thus, image texture analyses using gray level co-occurrence matrix, Voronoi tessellation and discrete wavelet transform based methods have been applied on turned surface images for extracting eight useful features to describe progressive tool flank wear. Prediction of cutting tool flank wear has also been performed using these eight features as predictors by utilizing linear support vector machine based regression technique with a maximum 4.9% prediction error.     

覆盖件模具拼接区表面微观几何形貌的反演分析

为提高车身覆盖件模具拼接区的加工质量,首先分析不同加工参数下拼接缝前后的表面形貌几何特性和残留高度的空间特性,然后基于小波包提取加工表面轮廓信号不同频段的能量熵特征,最后根据能量熵特征、材料去除率和刀具寿命预测函数反演表面形貌的加工参数。研究结果表明,基于反演分析方法得到的加工参数可以实现拼接区微观几何形貌的可控。     

基于动态树理论的刀具磨损监测技术

提出了基于动态树理论的刀具磨损监测方法,通过相关系数法提取传感器信号与刀具磨损最相关的几组特征,并采用具有局部记忆的B样条模糊神经网络建立刀具磨损量与声发射信号、切削力信号和振动信号特征之间的非线性映射关系,构造了任意加工条件下的刀具磨损监测系统,刀具磨损的识别结果由集成神经网络输出。试验结果表明,基于此方法构建的刀具磨损监测系统具有精度高、可靠度强、增殖性好和在线识别速度快等优点,值得工业推广。     

基于B样条模糊神经网络的刀具磨损监测

刀具状态监测是实现自动化加工和无人化加工的关键技术。本文使用切削力和声发射传感器监测金属切削过程,提出了基于B样条模糊神经网络作为刀具磨损量监测模型。该模型能够准确描述刀具磨损和信号特征之间的非线性关系,和常用的BP前馈神经网络相比,具有收敛速度快和局部学习能力等优点。试验结果表明:采用B样条模糊神经网络对提高刀具磨损在线监测的准确度和可靠度非常有效。