A location prediction method for work-in-process based on frequent trajectory patterns

Abstract

In the data-rich manufacturing environment, the production process of work-in-process is described and presented by trajectories with manufacturing significance. However, advanced approaches for work-in-process trajectory data analytics and prediction are comparatively inadequate. However, the location prediction of moving objects has drawn great attention in the manufacturing field. Yet most approaches for predicting future locations of objects are originally applied in geography domain. When applied to manufacturing shop floor, the prediction results lack manufacturing significance. This article focuses on predicting the next locations of work-in-process in the workshop. First, a data model is introduced to map the geographic trajectories into the logical space, in order to convert the manufacturing information into logical features. Based on the data model, a prediction method is proposed to predict the next locations using frequent trajectory patterns. A series of experiments are performed to examine the prediction method. The experiment results illustrate the impacts of the user-defined factors and prove that the proposed method is effective and efficient.

Vehicle Trajectory Prediction Method for Task Offloading in Vehicular Edge Computing

“…In order to verify the accuracy and efficiency of the method proposed in this paper, real-vehicle datasets and the bicycle check-in datasets publicly available on the Capital Bikeshare's website [24] were selected as the experiment datasets. RNN [13], Transformer [14] and T-pattern algorithms [17][18][19][20][21][22] were chosen as the baseline methods.…”

“…Refs. [ 19 , 20 , 22 ] used frequent trajectory patterns as one part of the trajectory prediction to address the prediction problem. However, current frequent pattern algorithms do not consider the local features of trajectories, which cannot guarantee both accuracy and efficiency.…”

“…Finally, we propose a search algorithm to address the optimization problem according to Equation (21). The search algorithm is to minimize the energy consumption in Equation ( 20) with the time consumption in Equation (19). The Algorithm 4 is as follows.…”

“…These methods also have high accuracy or efficiency. For example, vehicle trajectories can be predicted in real time by constructing T-pattern tree [18][19][20][21], but they have low accuracy. The frequent pattern prediction method proposed in [22] has a higher accuracy rate, but the method is not efficient enough to predict the vehicle trajectory in real time.…”

An Internet of Things based framework to enhance just-in-time manufacturing

“…This requires the planner to be familiar with all process capabilities such as changeover times, changeover patterns and the real lead times of each product, 10,11 which requires a high standard of manufacturing activities and a reliable and realistic planning system. Cai et al 12 developed a prediction model to predict the next locations of work-in-process in the workshop. IoT technologies can be used for capturing real-time production data and information, for example, the availability of materials, operators, machine tools, tooling, jigs and fixtures, which makes it possible to find out timely the production variations against scheduled plans, and once a variation is detected, the production line can react in real time.…”