Defective products are a major contributor toward a decline in profits in textile industries. Hence, there are compelling needs for an automated inspection system to identify and locate defects on the fabric surface. Although much effort has been made by researchers worldwide, there are still challenges with computation and accuracy in the location of defects. In this paper, we propose a hybrid semi-supervised method for fabric defect detection based on variational autoencoder (VAE) and Gaussian mixture model (GMM). The VAE model is trained for feature extraction and image reconstruction while the GMM is used to perform density estimation. By synthesizing the detection results from both image content and latent space, the method can construct defect region boundaries more accurately, which are useful in fabric quality evaluation. The proposed method is validated on AITEX and DAGM 2007 public database. Results demonstrate that the method is qualified for automated detection and outperforms other selected methods in terms of overall performance.

No abstract

No abstract

The paper mainly studied dosing pump unit and electronic control unit of exhaust after-treatment dosing system. It is based on SCR (selective catalytic reduction) technology. The ammonia combines with NO x to form harmless byproducts. New type metering pump based on stepper motor is adopted as AdBlue dosing equipment. The eccentric wheel drives plunger rod of pump. TMS320F28016 processor is the core chip in embedded control board developed. Suction speed is invariable and the fastest. Discharge speed could be dynamically changed as need. Requested dosing rate commands from the engine control unit are transmitted via CAN BUS, they can be responded within 2 milliseconds. Dosing rate of system can satisfy well requirement from 100 ml/h to 6000 ml/h. The precision of dosing rate can reach 1ml/h by setting PWM timer values. The dosing system developed can comply with State IV exhaust gas limits. This is an easy to control, very compact and inexpensive system. It is particularly suitable for retrofitting to trucks.

No abstract