Rescue work after a coal mine accident is fraught with challenges and dangers. Considering the safety of rescue workers and the urgency of a rescue mission, it is necessary to use coal mine rescue robots to perform the tasks of environmental detection and rescue. As a key part of the robot sensing system, a visual sensor can provide much information about a scene. Among vision sensor types, binocular vision has the advantages of being noncontact and passive, and it is the key technology for a robot to acquire obstacle information and reconstruct a three-dimensional scene. Therefore, coal mine rescue robots based on binocular vision have become a popular research topic in the field of mine safety. First, the research status of camera calibration and stereo vision matching for binocular vision is systematically introduced in this paper. Second, the latest research progress on coal mine rescue robots based on binocular vision is reviewed from the perspective of technological applications and development. Finally, the technical challenges and future development trends of binocular vision in coal mine rescue robots are described. INDEX TERMS Coal mine rescue robots, binocular vision, camera calibration, stereo vision matching.

To improve the accuracy of midterm power load forecasting, a forecasting model is proposed by combing kernel principal component analysis (KPCA) with back propagation neural network. First, the dimension of the input space is reduced by KPCA, then input the data set to the neural network model, optimized by particle swarm optimization. The monthly average of daily peak loads is forecasted to modify the daily forecast values and output the daily peak load in the end. Using the data provided by European Network on Intelligent Technologies to test the model, the mean absolute percent error of load forecasting model is only 1.39%. The feasibility and validity of the model have been proven.

No abstract

No abstract

No abstract