Autoencoder-based anomaly detection for surface defect inspection

In this paper, the unsupervised autoencoder learning for automated defect detection in manufacturing is evaluated, where only the defect-free samples are required for the model training. The loss function of a Convolutional Autoencoder (CAE) model only aims at minimizing the reconstruction errors, and makes the representative features widely spread. The proposed CAE in this study incorporates a regularization that improves the feature distribution of defect-free samples within a tight range. It makes the representative feature vectors of all training samples as close as possible to the mean feature vector so that a defect sample in the evaluation stage can generate a distinct distance from the trained center of defect-free samples. The proposed CAE model with regularizations has been tested on a variety of material surfaces, including textural and patterned surfaces in images. The experimental results reveal that the proposed CAE with regularizations significantly outperforms the conventional CAE for defect detection applications in the industry.     

全启发式教学法在“金属切削机床与刀具”课程中的应用

针对当代大学生的特点,阐述了来自于建构主义的全启发式教学方法的理论,对“金属切削机床与刀具”课程内容进行问题分解,采用以启发诱导、共同协作为核心的全启发式教学方法,对该课程的教学环节进行了合理的设计。     

非稀疏多核组合的支持向量回归方法

为了改善支持向量回归机的性能,本文提出了一种利用多核学习解决回归问题的算法(NS-MKR),算法对基本核函数的组合系数施加了Lp范数的约束(p>1),以得到组合系数的非稀疏解,并采用了两步优化方法,首先求解基于加权组合核的标准支持向量回归问题,用于学习拉格朗日乘子,然后采用简单的计算,求得基本核函数的组合系数,这两个步骤交替进行,直到满足事先定义的收敛准则。在人工数据集和真实数据集上的实验表明,相对于传统的单核和稀疏多核支持向量回归方法,本文提出的算法有更好的泛化性能。     

独立电源系统中的无刷双馈电机动态运行特性研究

针对独立电源系统中的无刷双馈发电机的特点,考虑到功率绕组和控制绕组的端电压随转速和负载的变化而变化,在无刷双馈电机d-q轴数学模型的基础上,建立了无刷双馈发电机在带载情况下的数学模型。并基于该数学模型,在matlab／simulink下建立了转速变化和负载变化的仿真模型,完成了其动态响应特性的研究。     

微波加热法合成蜂窝状堇青石载体Al2O3涂层

采用微波加热法在堇青石蜂窝陶瓷基体表面涂覆多孔Al2O3涂层,研究了制备条件对堇青石蜂窝陶瓷表面Al2O3涂层中Al2O3的质量分数的影响。通过BET、SEM对涂层结构及形貌进行了表征,结果表明,采用微波加热法制备的Al2O3涂层均匀、稳定,具有较大的比表面积、孔容和较高的Al2O3质量分数。     

离心铸造铸铁排水管生产中的一些问题

针对离心铸造铸铁排水管生产过程中存在的问题，如设备选型、涂料的影响，麻坑、针孔等铸造缺陷的产生原因等进行了分析和探讨。只要铸造生产工艺合理、涂料性能合适，即使是简易型离心铸管机也可生产出无铸造缺陷的高质量铸管。涂料性能与涂料使用方法强烈影响铸管表面质量和管模使用寿命。铸管外表面麻坑、针孔等缺陷的主要影响因素是涂料本身的性能和涂料使用工艺，铸管内表面龟纹等铸造缺陷的主要影响因素是铁水质量。     

New approach in tool wear measuring technique using CCD vision system

This paper suggests a reliable direct measuring procedure for measuring different tool wear parameters. Modern image processing techniques and machine vision systems today enable direct tool wear measurement to be accomplished in-cycle. The presented system is characterized by its measurement flexibility, high spatial resolution and good accuracy. The system consists of a light source to illuminate the tool, CCD camera, laser diod (used in conjunction with profile deepness assessment) with linear projector, grabber for capturing the picture, and a PC. The technique is specially characterized by its determination of profile deepness with the help of projected laser raster lines on a tool surface. So it has advantage comparing with other techniques, which can measure only 2D profiles. With the technique presented in this paper a 3D image of relief surface can be obtained without having need to employ a very complicated measuring system. All indirect methods like acoustic emission, force measurement, spindle current measurement, vibration sensors, etc. are very time consuming and demand very expensive subsidiary measurement equipment, compared with the method presented here.     

Automatic classification of defects on the product surface in grinding and polishing

Grinding and polishing are standard operations in material processing. It is important to inspect and classify the potential defects existing on the product surfaces after grinding and polishing in order to obtain high quality in both functionality and aesthetics. Post-processing handling can be carried out after the defects have been correctly classified. A vision system already exists to detect and classify defects based on captured grayscale images automatically. The system is able to find and locate the defects precisely, but is incapable of placing those defects into the right predefined classes. The old system classifies the defects 30% of the time into the 15 predefined classes based on shape features. In this paper, a new classification strategy has been introduced using diverse extracted features. In addition to shape features, some other feature extraction methods were tried, e.g. Laws filter bank, DCT (Discrete Cosine Transformation) filter bank, Gabor filter bank, and statistical features based on co-occurrence matrix. The Support Vector Machine (SVM) was used as a multi-class classifier with input of the extracted features. By combining the Gabor filter features and the statistical features, the classification rate of the system can reach 82% overall right rate, which is applicable practically.     

Adaptronic Vibration Damping for Machine Tools

A newly designed adaptronic component with a powerful piezo-stack actuator for active damping of machine vibrations is presented in this paper. Especially for machine tools with parallel kinematics, which feature lightweight structures and which are built in order to obtain high processing speeds, the active damping of machine vibrations is important to achieve the desired system performance. Extensive simulation studies with flexible multibody systems in order to test different control algorithms such as dissipative control, integrated force feedback or H₂/H_∞ control and recent experimental results show the high potential to improve the system behavior.