No abstract

No abstract

For precision inspection of free-form surface parts using non-contact measurement methods, the registration between the actual measurement model and the ideal design model is necessary.The traditional iterative closure point (ICP) method requires good initial parameters to obtain the global optimal transformation matrix, which is difficult to guarantee in the actual detection process. In order to improve the accuracy and robustness of free-form surface precision inspection, an Improved Whale Optimization Algorithm (IWOA) is proposed in this study.This algorithm can solve the required registration parameters by constantly updating the population. A measurement experimental system is designed to test the accuracy of blade registration. The performance of IWOA is evaluated by the actual measurement experiment, and the results are verified by a comparative study with Whale Optimization Algorithm (WOA), Lévy flight trajectory-based Whale Optimization Algorithm (LWOA), and Adaptive Whale Optimization Algorithm (AWOA). The surface registration errors are 0.1711mm for IWOA, 2.0015 mm for WOA, 1.2656 mm for LWOA, 2.8132 mm for AWOA and 2.1537 mm for ICP. The results show that the accuracy of IWOA is more than 7 times higher than other four algorithms. In general, the experiments indicate that IWOA has a good registration ability and can meet the needs of industrial measurement.

Abstract-In recent years, air pollution problem has been the focus of public attention. In this paper, we proposed an efficient algorithm to evaluate the Air Quality Index (AQI) based on image recognition technology. In offline stage, some distinctive features extracted from the photos which are captured by common digital cameras, and then a prediction model of backpropagation neural network (BPNN) is trained. In online stage, the feature vectors extracted from the images are fed to the trained BPNN model to output the AQI value. Experimental results show that the proposed algorithm can produce the AQI evaluation with a considerable accuracy 93.78%.

To improve the location accuracy of the vision system of a space manipulator, a new hybrid improved moth-flame optimization based on a differential evolution with global and local neighborhoods algorithm (HIMD) is proposed to optimize the pose of a target relative to a camera. Firstly, the non-linear optimization model is established according to the imaging rule and space geometry transformation principle of the vision system. Secondly, the initial population of pose parameters is generated by the moth-flame optimization (MFO) algorithm, and the population is updated by the improved MFO (IMFO). Finally, the new population is crossed, mutated and selected by the differential evolution with global and local neighborhoods (DEGL) algorithm, the population is iterated and updated continuously and the optimum pose can be obtained. The proposed algorithm is applied to the precision test in the measurement system of a space manipulator. The experimental results show that the average synthetic errors are 2.67mm for chaotic harmony search algorithm (CHS), 1.80mm for differential evolution with particle swarm optimization (DEPSO), 2.94 mm for the particle swarm optimization and gravitational search algorithm (PSOGSA), 2.13 mm for the DEGL algorithm, 2.56 mm for the MFO algorithm and 0.53 mm for the HIMD algorithm. This means that the accuracy of the HIMD algorithm is about four times higher than that of the MFO, PSOGSA and CHS algorithm and about three times higher than that of the DEGL and DEPSO algorithms. Therefore, the HIMD algorithm is superior to the other five algorithms for the non-linear optimization model of the pose.