Although significant progress has been made in precision machining of free-form surfaces recently, inspection of such surfaces remains a difficult problem. In order to solve the problem that no specific standards for the verification of free-form surface profile are available, the profile parameters of free-form surface are proposed by referring to ISO standards regarding form tolerances and considering its complexity and non-rotational symmetry. Non-uniform rational basis spline(NURBS) for describing free-form surface is formulated. Crucial issues in surface inspection and profile error verification are localization between the design coordinate system(DCS) and measurement coordinate system(MCS) for searching the closest points on the design model corresponding to measured points. A quasi particle swarm optimization(QPSO) is proposed to search the transformation parameters to implement localization between DCS and MCS. Surface subdivide method which does the searching in a recursively reduced range of the parameters u and v of the NURBS design model is developed to find the closest points. In order to verify the effectiveness of the proposed methods, the design model is generated by NURBS and the measurement data of simulation example are generated by transforming the design model to arbitrary position and orientation, and the parts are machined based on the design model and are measured on CMM. The profile errors of simulation example and actual parts are calculated by the proposed method. The results verify that the evaluation precision of freeform surface profile error by the proposed method is higher 10%–22% than that by CMM software. The proposed method deals with the hard problem that it has a lower precision in profile error evaluation of free-form surface.

A production status monitoring method based on edge computing is proposed for traditional machining offline equipment to address the deficiencies that traditional machining offline equipment have, which cannot automatically count the number of parts produced, obtain part processing time information, and discern anomalous operation status. Firstly, the total current signal of the collected equipment was filtered to extract the processing segment data. The processing segment data were then used to manually calibrate the feature vector of the equipment for specific parts and processes, and the feature vector was used as a reference to match with the real-time electric current data on the edge device to identify and obtain the processing start time, processing end time, and anomalous marks for each part. Finally, the information was uploaded to further obtain the part processing time, loading and unloading standby time, and the cause of the anomaly. To verify the reliability of the method, a prototype system was built, and extensive experiments were conducted on many different types of equipment in an auto parts manufacturer. The experimental results show that the proposed monitoring algorithm based on the calibration vector can stably and effectively identify the production information of each part on an independently developed edge device.

Due to obstructions in the natural environment, practical emotion recognition applications often experience reduced recognition accuracy. In order to address this technological challenge, this paper proposes an emotion recognition approach embedding adaptive dual-channel attention, specifically designed for recognizing facial expressions in obscured faces. This method employs an adaptive dual-channel attention mechanism to focus on the uncovered facial feature areas, enhancing the algorithm's capability to concentrate on features. Additionally, it utilizes a dual-stream residual multi-scale network to augment perception of features at various scales, thus improving recognition accuracy. Experimental evaluations conducted on the AffectNet dataset and SFEW 2.0 dataset demonstrate that this approach yields superior recognition accuracy compared to existing methods. This research provides an effective avenue for enhancing user experience in applications such as human-computer interaction.

This paper introduces a novel method for road target segmentation in the context of unmanned driving based on stereo disparity maps. The proposed method utilizes topological persistence threshold analysis to address the challenges associated with selecting appropriate threshold values. The approach involves converting 3D vehicle road images into uv-disparity maps, extracting road planes using v-disparity maps, and calculating occupancy grid maps using u-disparity maps. Persistence diagrams are then constructed by generating segmentation results under various threshold parameters. By establishing persistence boundaries in these diagrams, the most significant regions are identified, enabling the determination of robust segmentation thresholds. Experimental validation using KITTI stereo image datasets demonstrates the effectiveness of the proposed method, with low error rates and superior performance compared to other thresholding segmentation methods. The research holds potential for application in autonomous driving systems.