Search

The fault diagnosis of dimensional variation plays an essential role in the production of an automotive body. However, it is difficult to identify faults based on small labeled sample data using traditional supervised learning methods. The present study proposed a novel feature extraction method named, semi-supervised complete kernel Fisher discriminant (SS-CKFDA), and a new fault diagnosis flow for automotive assembly was introduced based on this method. SS-CKFDA is a combination of traditional complete kernel Fisher discriminant (CKFDA) and semi-supervised learning. It adjusts the Fisher criterion with the data global structure extracted from large unlabeled samples. When the number of labeled samples is small, the global structure that exists in the measured data can effectively improve the extraction effects of the projected vector. The experimental results on Tennessee Eastman Process (TEP) data demonstrated that the proposed method can improve diagnostic performance, when compared to other Fisher discriminant algorithms. Finally, the experimental results on the optical coordinate data proves that the method can be applied in the automotive assembly process, and achieve a better performance.

A new design of circular multi-pass cells (CMPC) with two rows of reflection spots on mirrors is presented. The effective optical path length (OPL) of this novel CMPC is double that of traditional CMPC with the same diameter and interval of spots. This OPL can be readily adjusted to have regular intervals by rough rotation adjustment. We achieved a spatial separation of pre- and post-transfer optical systems that was adequately large even in the cases with a large number of passes. Analytical chief ray tracing analysis and a generalized method for parameter determination for designing the cell are presented in detail. The stable condition of the double-row CMPC (DR-CMPC) is also derived by the ABCD matrix method. Designs with maximum effective OPL of 74.72 m, 48.67 m and 24.57 m are demonstrated and verified by ray tracing simulations within a 25 cm diameter DR-CMPC. An adjustment of the regular intervals to 1 m can be achieved in both designs. The overall astigmatism of the design with an effective OPL of 74.72 m is only 9.30 × 10−6 mm, which is four orders of magnitude smaller than that of the traditional CMPC with similar geometric parameters.

Vision-based methods for product quality inspection are playing an increasingly important role in modern industries for their good performance and high efficiency. A hybrid visual inspection system, which consists of an industrial robot with a flexible sensor and several stationary sensors, has been widely applied in mass production, especially in automobile manufacturing. In this paper, a rapid global calibration method for the hybrid visual inspection system is proposed. Global calibration of a flexible sensor is performed first based on the robot kinematic. Then, with the aid of the calibrated flexible sensor, stationary sensors are calibrated globally one by one based on homography. Only a standard sphere and an auxiliary target with a 2D planar pattern are applied during the system global calibration, and the calibration process can be easily re-performed during the system’s periodical maintenance. An error compensation method is proposed for the hybrid inspection system, and the final accuracy of the hybrid system is evaluated with the deviation and correlation coefficient between the measured results of the hybrid system and Coordinate Measuring Machine (CMM). An accuracy verification experiment shows that deviation of over 95% of featured points are less than ±0.3 mm, and the correlation coefficients of over 85% of points are larger than 0.7.

Industrial robots are expected to undertake ever more advanced tasks in the modern manufacturing industry, such as intelligent grasping, in which robots should be capable of recognizing the position and orientation of a part before grasping it. In this paper, a monocular-based 6-degree of freedom (DOF) pose estimation technology to enable robots to grasp large-size parts at informal poses is proposed. A camera was mounted on the robot end-flange and oriented to measure several featured points on the part before the robot moved to grasp it. In order to estimate the part pose, a nonlinear optimization model based on the camera object space collinearity error in different poses is established, and the initial iteration value is estimated with the differential transformation. Measuring poses of the camera are optimized based on uncertainty analysis. Also, the principle of the robotic intelligent grasping system was developed, with which the robot could adjust its pose to grasp the part. In experimental tests, the part poses estimated with the method described in this paper were compared with those produced by a laser tracker, and results show the RMS angle and position error are about 0.0228° and 0.4603 mm. Robotic intelligent grasping tests were also successfully performed in the experiments.

The acquisition of three-dimensional surface data plays an increasingly important role in the industrial sector. Numerous 3D shape measurement techniques have been developed. However, there are still limitations and challenges in fast measurement of large-scale objects or high-speed moving objects. The innovative line scan technology opens up new potentialities owing to the ultra-high resolution and line rate. To this end, a sensor for in-motion continuous 3D shape measurement based on dual line-scan cameras is presented. In this paper, the principle and structure of the sensor are investigated. The image matching strategy is addressed and the matching error is analyzed. The sensor has been verified by experiments and high-quality results are obtained.