Vehicle stowage and route planning are common problems for various delivery methods related to supermarket distribution. In order to resolve these problems, we propose capacitated route planning for supermarket order distribution based on order splitting. We construct the problem model with the goal of minimizing the total cost of delivery. Combined with real cases, an improved gray wolf optimization algorithm adding a genetic mutation operation is proposed. The effectiveness of the model and algorithm is verified by comparing performance with the genetic algorithm. The results show that when the total demand of supermarkets is close to an integer multiple of the vehicle capacity, our proposed planning approach is better. This is mainly reflected in the fact that the order splitting plan can make full use of vehicle capacity, reduce the empty driving rate for vehicles, and reduce the total distribution cost.
Capacity prediction plays an important role in smart logistics, and its results are important for improving the accuracy of capacity scheduling and truck-cargo matching. Existing researches on capacity prediction in urban road networks aim to determine the number of available vehicles in future periods, while the problem of capacity prediction in bulk logistics aims at predicting the information on the trucks (e.g. the truck’s identity document (ID)) to carry certain types of goods for different flows, which is closely related to whether the trucks can return to the steel plant within the expected time (called capacity accessibility). In the case of bulk logistics, it is necessary to take into account the impact of the time spent on the two trips from the steel plant to the customer’s business and back to the steel plant. Since trucks need to stop several times in the long-distance transportation process but the length of stopping time varies, the uncertainty of stopping time makes the accurate prediction of transportation delivery time difficult. In addition, the freight platform only assigns capacity to one-way transport tasks (i.e. from the steel plant to the customer’s business), and the return trip (i.e. back to the steel plant) is determined by the truck drivers, which leads to the lack of return trajectory and poses a challenge to predict the return time of trucks to the steel plant. In order to solve the above challenges, based on the data sets of waybills, trucks, trajectories, and transport endpoints of logistics enterprises, we extract the stay behavior features, transport endpoint features, and environmental features. Then, the self-attention mechanism is introduced to obtain the weights of different features on the time consumption of two trips respectively to further improve the accuracy of capacity accessibility prediction. On this basis, a truck capacity prediction method based on self-attention mechanism is proposed, including capacity candidate set generation based on historical flow similarity, capacity accessibility prediction based on self-attention mechanism, and capacity carrier flow prediction based on long short-term memory (LSTM). Finally, the experimental results of comparison experiments on real logistics datasets show that the proposed method has higher prediction accuracy and can provide powerful decision support for the optimization of capacity scheduling in bulk logistics.
Trajectory data are typically large in scale and require frequent updates; hence, there are high performance requirements for trajectory queries. In order to improve the query efficiency of trajectory data, a two-level trajectory partition algorithm is presented herein. In the first partition, trajectory data was divided into sub-trajectories based on optimized minimum bounding rectangle (MBR) to improve the approximate effect of trajectory data. In the second partition, the sub-trajectories were grouped by the grid structure according to spatio-temporal characteristics. A packing method of R-tree was proposed based on the partition algorithm, and the divided trajectory data was packed into the R-tree from bottom to top. Finally, compared with a method based on the average number or average size of trajectory segments, experimental results show that the proposed method offers better query performance than the two other methods based on the average number of trajectory segments and combined movement features; in fact, the query efficiency is improved by 43% and 30.5%, respectively.
With digital transformation and the development of iron and steel logistics, the scale of iron and steel logistic data has rapidly expanded, and traditional relational databases can no longer meet the storage and query needs. Considering that a distributed not only structured query language (NoSQL) database has a simple expansion capability, fast reading and writing speeds, and low cost, in this study, distributed cloud storage and NoSQL technologies are used to store and build indexes for massive steel logistic data, improving the accuracy of the storage capacity and query performance of the logistic data. First, Spark is used to associate and fuse the data from different sources, and then store and manage the historical and real-time data generated by the freight platform in a hierarchical manner. It then builds spatiotemporal and attribute indexes for the three types of queries mainly involved in steel transportation to achieve an efficient query of multi-source logistic data. Finally, the experimental results based on real steel logistic data show that the proposed scheme is superior to traditional relational database methods in terms of data writing, storage, and querying, and can effectively support the storage and querying of massive logistic data.
A long short-term memory (LSTM)-based network employing a fault prediction algorithm and tree-structured network employing a minimal cost repair generation algorithm are proposed in this study to predict possible anomalies using a large amount of historical data for the effective identification of fault treatments. In addition, the minimal cost repair operation sequence was generated based on dynamic programming; the sequence of valid operation orders could be quickly generated. The results of this study indicate that the proposed networks could effectively reduce the dispatch error rate, improve the dispatch efficiency, and reduce the failure time of power grid systems, and therefore can be used to reduce the economic loss caused by the aforementioned factors.
As the core components of aircraft, engines play a vital role during flight. Accurate prediction of the remaining useful life of the aeroengine can help prognostics and health management, thus preventing major accidents and saving maintenance costs. In view of the lack of consideration of different time steps and the relationship between different sensors and operating conditions in existing methods, a remaining useful life prediction method based on the Transformer was proposed, which fuses multi-feature outputs from different encoder layers. This method selects two input data with different time steps, analyzes the relationship between the sensors using permutation entropy, and extracts features independently from the operating condition data. The experimental results on the public aeroengine dataset CMAPSS (Commercial Modular Aero-Propulsion System Simulation) show that the proposed method is superior to other advanced remaining useful life prediction methods.
中国综合性科技类核心期刊(北大核心)
