Search

The conventional method of PM2.5 prediction requires high-precision instruments to obtain data on the concentration of pollutants, resulting in a high prediction costs. In this work, we attempt to use image data to estimate PM2.5 concentration. The concentration of atmospheric PM2.5 is closely linked to the image’s dark channel intensity, contrast, and color difference of HSI. The increase in atmospheric PM2.5 concentration leads to a decrease in the non-sky area dark channel intensity, image contrast, and HSI spatial color difference. In this paper, a Column-Generation PM2.5 prediction model based on image mixture kernel was proposed by analyzing the relationship between PM2.5 and image features. First, the sampling period was taken as 1 h, and 8:00–17:00 was taken as the sampling range daily. The scene images were recorded in different weather conditions, and five image features were extracted, including contrast, dark channel intensity, and HSI color difference. Secondly, the image data has the characteristics of large sample size and uneven distribution, and the prediction model consists of a single kernel function, which makes it difficult to meet the prediction accuracy requirement. Therefore, the linear kernel function, polynomial kernel function, and Gauss kernel function were chosen to construct a composite model according to the concept of kernel structure from simple to complex. Then each kernel's Gram matrix was calculated based on training samples, and all gram matrices were placed into a mixture kernel matrix. Using the column generation algorithm and mixture kernel matrix, the prediction model was developed and the parameters of the model were solved. Finally, simulation experiments were performed; the results show that the prediction model based on the image mixture kernel of Column-Generation PM2.5 can meet the prediction accuracy requirements. The model has higher prediction accuracy and better model stability in comparison with the single-kernel prediction model. A computational complexity analysis shows that the prediction model based on the image mixture kernel of column-generation PM2.5 has no significant increase in computational complexity in comparison with the one-kernel prediction model.

A cutting stock algorithm based on four-block layout was proposed to solve the two-dimensional plate shearring and punching of circular parts. With this layout, a sheet was divided into four blocks. Only the strips with the same direction and length were arranged in each block, and several rows of the same circular parts were arranged in the strips. A four block layout method for generating circular parts on a single sheet by constructing a layout algorithm. Firstly, the layout of circular parts in the strips was determined. Secondly, recursive algorithm was constructed to generate the layout of the strips in blocks. Finally, implicit enumeration algorithm was used to determine the optimal four-block partition. The column generation algorithm was used to call the above layout algorithm to generate a number of different layouts. Based on the simplex principle, a group of layouts were selected to form the cutting plan, and the decimal solution was rounded. The results showed that the plate utilization ratio of the algorithm in the study is 0. 49%, 0. 32%, 6. 04% and 1. 50% higher than those of the four literature algorithms, respectively, and the calculation time can meet the needs of practical applications. [ABSTRACT FROM AUTHOR]

The problem of disrupted flight recovery is a very complicated real-time network optimization problem, which belongs to NP-hard problem. Considering the situation caused by the shortage of aircraft resources, the closure of airports and the unplanned maintenance, this paper adopts multiple recovery options, such as flight delays, flight cancellations, flight swaps and so on. Based on Dantzig-Wolfe decomposition principle, the mathematical optimization models of master problem and sub-problem are established respectively. And column generation algorithm is introduced to solve this large integer programming problem. In the solving process, first, the initial feasible routes are constructed and the master problem is solved with CPLEX software based on the lines. Secondly, in view of the characteristics of the problem, some properties are proposed, then the sub-problem is solved by using the improved "label-setting algorithm", and in each iteration, multiple columns with reduced cost are added to reduce the number of iterations, then the branch and bound algorithm is used to handle the non-integer solutions. Finally, the correctness and efficiency of the method are verified by testing the practical instances of various scales, and the test results are analyzed and summarized. [ABSTRACT FROM AUTHOR]