Determination of the Reliability of Urban Electric Transport Running Autonomously through Diagnostic Parameters

Abstract

The urban transport network involves complex processes, operating 24 h a day and 365 days a year. The sustainable development of the urban transport network using electric buses and trolleybuses that run autonomously is an urgent task since the transport network performs integral social functions and is the transport artery of any urban center. The social and economic life of a city as a whole depends on the reliability of the transportation network. A theory is proposed for the technical and economic evaluation of reliability improvement in electric buses and trolleybuses running autonomously, which enables the determination of the reliability parameters of electric buses and forecasts for the future from the point of view of optimal economic costs for the operation of electric equipment in electric buses. As a result of the application of the proposed theory, it was found that increasing the reliability of the transportation fleet can lead to a decrease in both specific operating costs and capital investments in the development of the fleet. This is achieved as a result of increasing the annual productivity of vehicles by reducing the time they are out of service to eliminate the consequences of failures and carry out maintenance and repair. The conducted experiments confirmed that the theory and methodology of optimal reliability level selection not only enable the rational use of the material resources of the urban transport network but also the release of funds for its scientific and technical development by reducing the number of failures in the electrical equipment of transport systems by 14%.

Mathematical Logic Model for Analysing the Controllability of Mining Equipment

“…The proposed mathematical logic model for analysing the controllability of mining equipment, taking into account its resource and diagnostic parameters including testability, correlates with the general reliability models described in [65,67,80,81], which allows us to speak about its adequacy and applicability to the analysis of mining equipment.…”

“…This study analysed diagnostic systems in order to determine the optimal number of test points to guarantee the maximum diagnostic performance and hardware implementation, given the specific requirements and purpose of a system. Testability is a measure of the ability of a diagnostic system to detect and localise defects in an object [65,66]. It depends on the number of control points and their placement.…”

Analysis of a Predictive Mathematical Model of Weather Changes Based on Neural Networks

“…Therefore, grouping neural networks integrates these independent networks to improve the generalisation ability. This method also guarantees an increase in accuracy in terms of a standard deviation [63][64][65][66].…”

“…The first of these neurons has a vector of weights, which is the sum of the vector of weights of the original neuron, and vectors of changes in the weights of one of the preferential directions. The summation of the vectors of weight changes in the other preferential direction and the vector of weights of the original neuron results in the synaptic weights of the second new neuron [64].…”

“…The first of these neurons has a vector of weights, which is the sum of the vector of weights of the original neuron, and vectors of changes in the weights of one of the preferential directions. The summation of the vectors of weight changes in the other preferential direction and the vector of weights of the original neuron results in the synaptic weights of the second new neuron[64].It is necessary to split neurons whose change vectors have two preferential directions because the presence of such neurons leads to oscillations during training by backpropagation. When training the method with an integral error function, the presence of such neurons leads to a hit in the local minimum with a large error value.The splitting algorithm includes the construction of a covariance matrix of vectors of changes in synaptic weights and the calculation of eigenvectors and eigenvalues of the obtained matrix using the iterative Oja algorithm, according to which stochastic gradient lifting and Gramm-Schmidt orthogonalisation are performed[65].It is necessary to consider a single neural network that is trained on some dataset.…”