Техосмотр – не догма, а средство обеспечения безопасности дорожного движения
The questions of improving the management of maintenance vehicles. The analysis of the regulatory framework for the management of maintenance, and assesses its impact on road safety
Predictive maintenance is a powerful maintenance strategy that makes it possible to significantly reduce operation and maintenance costs of public, commercial and industrial environments. It is a complex data-driven process, which tries to forecast future states of company assets. On one hand it prerequisites condition monitoring of components on machine level. On the other hand it demands the integration of the collected data with other management information systems. Digitization and especially the advent of big data science bring along promising opportunities to create effective smart monitoring and predictive maintenance applications. The aim of this research is to examine the possibilities of a predictive maintenance framework based on the design principles of Industry 4.0 and recent developments in distributed computing, Big Data and Machine Learning. It introduces numerous enabling technologies such as industrial Internet of things, standardized communication protocols, as well as edge and cloud computing. Moreover, it takes a deeper look at data analytical techniques and tools, and analyses performance of well-known machine learning algorithms. Paper proposes architecture of a predictive maintenance framework based on existing software and hardware solutions. As a proof of concept, a real-life smart heating, ventilation, and air conditioning (HVAC) application system is created and tested to demonstrate the possibilities of the proposed PdM framework.
Planning electric-rolling-stock (ERS) maintenance in conditions of limited resources can be carried out based on the following criteria of efficiency of construction of the cycle diagram of the electric rolling stock: meeting the requirements of the railway-traffic safety provided by adjusting the planned movement time of the electric rolling stock for the purpose of not allowing an excessive lapse of time between the maintenance over that permissible and uniformity of maintenance. The solution of the set problem using the graph theory allows obtaining the whole set of the permissible values of maintenance and selecting a value that, on the one hand, corresponds to the planned train time schedule (PTTS) and, on the other hand, differs minimally from the optimal with respect to the selected criterion. This takes a significant amount of time. The problem can be quickly solved using a genetic algorithm. The introduction of a new criterion—total excess time lapse between maintenance works over the permissible interval—allows obtaining the solution with any initial data, which is not always achievable when using the uniform-maintenance criterion. The crossover and permutation algorithm implemented within the genetic algorithm is adapted taking into account considering the peculiarities of the agents engaged in solving the problem that has been set out. We have studied the possibility of using various types of crossover and permutation to construct the cycle diagrams and influence of the parameters of the genetic algorithm on the results. The obtained analytical results are tested for the conditions of the Moscow subway.