Search

This paper describes an automated visual inspection system for the size measurement of workpieces, widely applicable to industrial on-line and real-time products inspection such as bearing, gear and so on. The systematic makeup, basis demands and CCD-based size measurement principle is introduced. To increase the efficiency and effect of pre-processing image, take a bearing as an example, fast algorithm for 2-D median filter is advanced and investigated. Also, based on the fundamental theory of the wavelet transform, an edge detection method is successfully used in the feature extraction of a bearing image. Finally, with the studied automated visual inspection system, the out-diameter of a bearing is inspected and analyzed. The result meets demands and shows the system has a broad applied foreground

Condition monitoring is very important in machinery engineering study. In most conditions, normal signals are acquired easily but fault samples are difficult to be gained. Because of lacking enough fault samples, the machine diagnosis meets difficulties. Support vector data description (SVDD) is a single classifier and it can distinguish the normal and fault condition just using normal samples. In this paper we first describe the basic algorithm of SVDD. 5-cross validation is used as model selection to optimize the parameter of SVDD. Extracting two-dimension spectrum entropy of signals as the input of the SVDD classifier, we got high classification. Compared neural network (ANN) with SVDD, the experiment result represents that in the environment which lacks of enough fault samples condition monitoring, SVDD has better classification than ANN.

Microbiological fermentation is a kind of complicated batch process that is severely nonlinear and time variant. There are many process parameters need to monitor and control in order to make the microbiological fermentation process successful. So it is important to measure the process variables. But the instrumentation and sensors available for fermentation control do not cover all the desirable or necessary measurements. In fermentation processes, many important internal variables can't be measured. Soft sensor has become an indispensable method to measure internal variables in fermentation processes. In this paper, we propose a new method of soft sensor constructed with generalized support vector machine for microbiological fermentation. We discuss how to construct soft sensor with generalized support vector machine and least square generalized support vector machine respectively. This method was compared with neural network in the experiment of soft sensor construction. Experiment results demonstrate this method of constructing soft sensor in microbiological fermentation is very valid.