With the continuous development of engineering construction in China, more and more large-section highway tunnels have emerged. Different geological engineering environments determine the diversity of construction plans. The determination of construction plans and the prediction of tunnel deformations have always been the key points of engineering construction. In this paper, we use numerical simulations to determine specific construction parameters in the context of actual highway tunnel projects, and then use deep learning methods to predict deformation during tunnel construction, thus providing guidance for construction. We have found that: (i) Different excavation sequences and excavation depths have different effects on the surrounding rock deformation around the tunnel. The optimal excavation sequence through numerical simulation in this study is symmetrical excavation, and the excavation depth is 2 m. (ii) Numerical simulation based on Long Short-Term Memory (LSTM) algorithm is used to predict the tunnel deformation. It is found that the prediction results of the LSTM algorithm are more consistent with the actual monitoring data. (iii) Multi-step prediction is more important for engineering guidance, and three-step prediction can be considered during the process of engineering construction. Therefore, the machine learning algorithm provides a new method for engineering prediction.
Electric vehicles (EVs) are a promising option to reduce air pollution and shipping costs, especially in urban areas. To provide scientific guidance for the growing number of logistics companies using EVs, we investigated an electric-vehicle-routing problem with simultaneous pickup and delivery that also considers non-linear charging and load-dependent discharging (EVRPSPD-NL-LD). The objective was to minimize the total number of EVs and the total working time, including travel time, charging time, waiting time, and service time. We formulated the problem as a mixed integer linear program (MILP), and small-size problems could be solved to optimality in an acceptable amount of time using the commercial solver IBM ILOG CPLEX Optimization Studio (CPLEX). In view of the fact that the problem is NP-hard, an adaptive large neighborhood search (ALNS) metaheuristic method was proposed to solve large-size problems. Meanwhile, new operators and a time priority approach were developed to provide options for different scenarios. The results of our computational investigation and sensitivity analysis showed that the proposed methods are effective and efficient for modified benchmark instances.
In this paper, we use intelligent scheduling technique to propose an electric vehicle routing problem with simultaneous pickup and delivery (EVRPSPD) model which considers the load-dependent discharging (LD). The model aims to minimize the working time including travel time, charging time, service time, and waiting time. In small-scale problems, rational routing decisions can be obtained directly using the commercial software CPLEX. In addition, we propose an adaptive large neighbourhood search algorithm (ALNS) for this problem, which can solve large-scale problems and obtain feasible solutions in an acceptable amount of time. Our computational investigation indicates that load-dependent discharging is non-negligible for the problem.
Software Engineering, which is an information technology course, is to cultivate students’ comprehensive application ability in the process of software development. This article aims to study the blended learning mode of software engineering based on multimedia information technology – Study Master platform. The teaching team also uses the big data techniques to reshape teaching objectives, reconstruct teaching content, strengthen key and difficult points. The Study Master platform provides videos, online tests, development materials, etc. It can not only make students more flexible to master their own learning time, but also make them more actively participate in the course learning. The strategies of Study Master platform, online courses, flipped learning are all throughout the whole teaching process. Moreover, various evaluation methods are adopted, including online process assessment, practice assessment, and traditional examination. The survey is also sent to learners which is used to verify the effect of the Study Master platform.