It is a very complicated work for optimizing the train operation diagram for railway enterprise. In order to improve the quality and reduce the computing time of train operation diagram, an initial relaxant train operation diagram is drawn ignoring the constraints among different train running lines firstly in this paper. Secondly based on this initial relaxant train operation diagram, through devising the multi-parallelogram and weighted directed graph representation of train operation diagram, the train operation diagram is optimized via the directed graph by the strategies such as exchanging operation order, increasing dwell time and expanding departure time, and then the sequencing optimization method is designed for drawing train operation diagram using computer, which aim to minimize the total passenger train travel time under the constraints of train arriving-departing interval time, train minimum dwell time, train travel time, train departure time and comprehensive maintenance time. A numerical example is given to show that this sequencing optimization method can effectively draw the passenger train operation diagram of high-speed railway

For the method calculating the benefits gotten by transferring the wagons at technical stations without sorting operations, two different calculating methods are brought forward at present. This paper firstly calculates the wagon hours consumed both when the basic scheme is applied and the scheme in which the trough wagon flows passing the technical station without shunting operations is applied, and then deduces a formula to calculate the wagon hours saved by through wagon flow passing technical station without sorting operations and analyzes deeply the affecting factors. As a result, it is found that the two calculating methods are the special cases of it. Because in the calculating process the influence of through wagon flow passing the station to the staying time at the station has been taken into account, the method mentioned above is more complete, and could provide a theoretical basis for the calculation.

In order to improve the efficiency of selecting the optimal scheme from the delivering and fetching shunting schemes of through wagon flow to and from the enterprise dedicated lines which are located in radial shape, the taboo search algorithm is applied in the process finding the optimal solution. The objective function is directly used as the fitness function, and the solution generated by exchanging the wagon group delivering order of one dedicated line with another is taken as the new solution; the taboo list is two-dimensional array, and a fixed value is given as the taboo length; if the evaluation value of the current optimal solution is superior to the historical one, the taboo rules will be defied and the current optimal solution be directly accepted; once the iteration number reaches the predetermined number, the calculating process will be terminated. The simulation results verify the effectiveness of the Taboo search algorithm to the problem, and show that the bigger the number of the dedicated lines, the more the number of equivalent schemes and the higher the searching efficiency is. And the smaller the number of the equivalent schemes, the bigger the search scope is. If the number of the dedicated lines is not more than 8, the processing time by computer is not longer than 15 milliseconds.

Herein, on the basis of a distributed AI cluster, a real-time video analysis system is proposed for edge computing. With ARM cluster server as the hardware platform, a distributed software platform is constructed. The system is characterized by flexible expansion, flexible deployment, data security, and network bandwidth efficiency, which makes it suited to edge computing scenarios. According to the measurement data, the system is effective in increasing the speed of AI calculation by over 20 times in comparison with the embedded single board and achieving the calculation effect that matches GPU. Therefore, it is considered suited to the application in heavy computing power such as real-time AI computing.

This paper studies the Electronic Device Testing Machine Allocation Problem (EDTMAP), aiming to improve the production of electronic devices and reduce the scheduling distance of testing machines through reasonable machine allocation. Firstly, a mathematical model is formulated for the EDTMAP to maximize both production and the opposite of the scheduling distance of testing machines. Secondly, we develop a Discrete Multi Objective Artificial Bee Colony (DMOABC) algorithm to solve the EDTMAP. A crossover operator and a local search operator are designed to improve the exploration and exploitation of the algorithm, respectively. Some numerical experiments are designed to evaluate the performance of the proposed algorithm. The experimental results demonstrate the superiority of the proposed algorithm compared with NSGA --Ⅱ and SPEA2. Finally, the mathematical model and the DMOABC algorithm areapplied to a real world factory that tests radio frequency modules. The result also verifies our method can significantly improve production and reduce the scheduling distance of testing machines.