Grey theory–based BP-NN co-training for dense sequence long-term tendency prediction

PurposeThe purpose of this paper is to solve the problems existing in topic popularity prediction in online social networks and advance a fine-grained and long-term prediction model for lack of sufficient data.Design/methodology/approachBased on GM(1,1) and neural networks, a co-training model for topic tendency prediction is proposed in this paper. The interpolation based on GM(1,1) is employed to generate fine-grained prediction values of topic popularity time series and two neural network models are considered to achieve convergence by transmitting training parameters via their loss functions.FindingsThe experiment results indicate that the integrated model can effectively predict dense sequence with higher performance than other algorithms, such as NN and RBF_LSSVM. Furthermore, the Markov chain state transition probability matrix model is used to improve the prediction results.Practical implicationsFine-grained and long-term topic popularity prediction, further improvement could be made by predicting any interpolation in the time interval of popularity data points.Originality/valueThe paper succeeds in constructing a co-training model with GM(1,1) and neural networks. Markov chain state transition probability matrix is deployed for further improvement of popularity tendency prediction.

Availability models of series mechanical systems considering failure and maintenance dependencies

Availability models of series mechanical systems based on system working mechanisms are developed by integrating the statistical characteristics of stress, strength, and maintenance parameters. Failure, maintenance, and strength degradation path dependence are taken into consideration in the proposed models without empirical parameters. Moreover, the problem of inconsistency between the failure rate and the availability in time is pointed out, and a method to solve this problem is proposed. Monte Carlo simulations are carried out to verify the proposed models. In addition, numerical examples are given to illustrate the established method. The results show that failure, maintenance, and strength degradation path dependence and time scale inconsistence in the state transition probability matrix have significant influences on the availability of mechanical systems. The proposed models provide an analytical basis for quantitative availability estimation, optimization design, and maintenance strategy decision-making of mechanical systems.

Safety and Risk Management

The article is devoted to the problem of creating a system of security and risk management. Formulated in relation to the process of movement of trains:- factor of safety of the train - the probability of traversing the trains on a particular route without transfer of its movement in a dangerous condition;- a measure of risk of the transfer movement of the train in a dangerous state - transition probability of motion in a dangerous state when the movement of trains on a given route.The objectives of security and risk management are: to provide values of their indicators are not worse than normative, namely, the values of the performance security shall be not less than the normative, and the values of indicators of risk - not more than normative. Proposed functional framework and organizational structure for the management of safety and risks.