No abstract

PurposeAs an important product characteristic, maintainability is recognized as a highly significant factor in the economic success of engineering systems and products. Based on virtual reality technology, this paper aims to create an intuitive, immersive and interactive environment for product maintenance. In order to analyze and evaluate the product maintainability in a virtual maintenance environment, fuzzy comprehensive evaluation is used. At the early design stage, maintainability influencing factors are analyzed and the whole maintainability evaluation of the product is given by using fuzzy comprehensive evaluation method in virtual maintenance environment.Design/methodology/approachThe paper provides a fuzzy comprehensive evaluation method for product maintainability evaluation in virtual environment.FindingsFuzzy comprehensive evaluation is used to evaluate product maintainability in virtual environment, and the application of virtual maintainability system is expanded.Originality/valueAccording to maintainability requirement, the maintainability index set is built in this paper, and fuzzy comprehensive evaluation method is used to evaluate product maintainability in virtual maintenance environment at stage of early design.

No abstract

Accurate metro ridership prediction can guide passengers in efficiently selecting their departure time and simultaneously help traffic operators develop a passenger organization strategy. However, short-term passenger flow prediction needs to consider many factors, and the results of the existing models for short-term subway passenger flow forecasting are often unsatisfactory. Along this line, we propose a parallel architecture, called the seasonal and nonlinear least squares support vector machine (SN-LSSVM), to extract the periodicity and nonlinearity characteristics of passenger flow. Various forecasting models, including auto-regressive integrated moving average, long short-term memory network, and support vector machine, are employed for evaluating the performance of the proposed architecture. Moreover, we first applied the method to the Tiyu Xilu station which is the most crowded station in the Guangzhou metro. The results indicate that the proposed model can effectively make all-weather and year-round passenger flow predictions, thus contributing to the management of the station.

Sometimes subway stations and trains can be very crowded for large passenger flows. However, some stations and trains may be vulnerable when natural or man-made disasters happen, thus the safety of passengers and stuff is threatened. Therefore, it is meaningful to make a deep analysis to these disasters that may happen in subway stations and trains. By collecting cases of accidents include fire disaster, terrorist attack, flood, earthquake and stampede that happened in subway stations or on trains around the world, the causes, consequence and their own characters were analysed. Besides, some recommendations and beneficial measures aim to prevent these disasters mentioned above were also presented and discussed.