Olga Kochueva has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    The Weights Reset Technique for Deep Neural Networks Implicit Regularization

    by Grigoriy Plusch, Sergey Arsenyev-Obraztsov, Olga Kochueva

    We present a new regularization method called Weights Reset, which includes periodically resetting a random portion of layer weights during the training process using predefined probability distributions. This technique was applied and tested on several popular classification datasets, Caltech-101, CIFAR-100 and Imagenette. We compare these results with other traditional regularization methods. The subsequent test results demonstrate that the Weights Reset method is competitive, achieving the best performance on Imagenette dataset and the challenging and unbalanced Caltech-101 dataset. This method also has sufficient potential to prevent vanishing and exploding gradients. However, this analysis is of a brief nature. Further comprehensive studies are needed in order to gain a deep understanding of the computing potential and limitations of the Weights Reset method. The observed results show that the Weights Reset method can be estimated as an effective extension of the traditional regularization methods and can help to improve model performance and generalization.


  • Open Access

    Analysis of approximations of the gas compressibility factor derived from genetic algorithms

    by Olga Kochueva, Vladislav Zadorozhnyy

    Hydraulic calculations are the primary tool for rational technical decisions related to the design and operation of pipeline systems. The compressibility factor is introduced into the gas equation of state to account for its real properties and depends on the pressure, temperature, and gas component composition. At present, the search for an accurate and computationally efficient approximation for the compressibility factor remains an urgent problem. This paper presents a methodology for constructing an approximation based on symbolic regression, and the proposed dependencies analysis provided. The average relative error of the presented models is 0.03%.


  • Open Access

    Renewable k-Out-of-n System with the Component-Wise Strategy of Preventive System Maintenance

    by Vladimir Rykov, Olga Kochueva, Elvira Zaripova

    At the SMARTY-22 conference, a review of the regenerative methods development was presented, including its application to the study of a non-renewable k-out-of-n system. This paper develops the previous study for the renewable k-out-of-n system, including an investigation different preventive maintenance strategies based on the system state observation. We also include the review of Smith’s regeneration idea development. Some new results are presented that form the basis for an algorithm for comparing preventing maintenance strategies with respect to the maximization of the availability factor. A numerical study was conducted for the 4-out-of-6 and 4-out-of-8 models. The study demonstrates the sensitivity of decision making to the shape of the repair time distribution.


  • Open Access

    Sensitivity Analysis of Risk Characteristics of Complex Engineering Systems: An Application to a Subsea Pipeline Monitoring System

    by Vladimir Rykov, Olga Kochueva, Mais Farkhadov, Elvira Zaripova, Anna Zhaglova

    One of the problems of risk analysis of complex engineering systems is the uncertainty of initial information about the time and damage associated with occurrence and development of the risk situation. The paper proposes a methodology and procedure for constructing a risk tree, loading it with initial data, calculating the corresponding characteristics: the distributions of time to reach the intermediate and main risk events and of associated with them damages, as well as their moments. Methodology involves the construction of the most dangerous path of risk situation development with respect to different criteria as well as analysis the sensitivity of risk characteristics to the initial information. The proposed approach is applied to a model of an automated system for remote monitoring of underwater gas pipeline. The proposed methodology and its implementation on a real-world example constitute the novelty of the work.


  • Open Access

    Experimental Study of Wave Processes in Main Gas Pipelines under Normal Operating Conditions

    by Mikhail Sukharev, Olga Kochueva, Anna Zhaglova

    The article presents the results of processing non-emergency pressure measurements that are transmitted via the SCADA hardware and software system to the control center of the main gas pipeline. SCADA is widely used for real-time control of the modes of gas transmission systems. However, the data provided by SCADA contain some information that is not fully analyzed. The performed processing of pressure measurements is a passive experiment aimed at a deeper understanding of the flow processes that occur during the flow of gas in industrial pipelines of high power. As a result of the experiment, four types of wave phenomena were found: single waves of (a) compression and (b) decompression that were both damped as they moved along the pipe, (c) oscillations with an amplitude and frequency practically unchanged in a fixed section within a period of about 2 h, and (d) wave phenomena with a sharply changing amplitude and frequency within a period of several minutes. The characteristics of wave processes, such as the speed of movement and the decreasing or attenuating amplitude of oscillations, were evaluated. For evaluation, models were built that take into account the specifics of information transfer procedures, namely, SCADA’s representation of continuous functions in a discrete form. The results obtained can be used as an additional tool for searching for leaks, such as in fistulas and unauthorized tie-ins, allowing us to more accurately separate the useful signal from the noise. The question is raised about the adequacy of the one-dimensional model for describing the flow processes in the zones of large gradients of regime parameters. The reasons for possible inadequacy and ways to overcome it are indicated.


  • Open Access

    Preventive Maintenance of k-out-of-n System with Dependent Failures

    by Vladimir Rykov, Olga Kochueva

    The paper investigates a model of a k-out-of-n system, the residual lifetime of which changes after failures of any of its components. The problem of a Preventive Maintenance (PM) organization as advice to the Decision Maker (DM) for such a system is considered. The purpose of this paper is to propose a mathematical model of the k-out-of-n system to support DM about PM. For most practical applications, it is usually possible to estimate the lifetime distribution parameters of the system components with limited accuracy (only one or two moments), which is why special attention is paid to the sensitivity analysis of the system reliability characteristics and decisions about PM to the shape of system components lifetime distributions. In the numerical examples, we consider the 3-out-of-6 model discussed in our previous works for two real systems. The novelty, significance, and features of this study consist of the following, after the failure of one of the system components, the load on all the others increases, which leads to a decrease in their residual lifetime. We model this situation with order statistics and study the quality of PM strategies with respect to the availability maximization criterion. At the same time, we are focusing on the study of the sensitivity of decision-making to the type of lifetime distribution of system components.


  • Open Access

    Data Analysis and Symbolic Regression Models for Predicting CO and NOx Emissions from Gas Turbines

    by Olga Kochueva, Kirill Nikolskii

    Predictive emission monitoring systems (PEMS) are software solutions for the validation and supplementation of costly continuous emission monitoring systems for natural gas electrical generation turbines. The basis of PEMS is that of predictive models trained on past data to estimate emission components. The gas turbine process dataset from the University of California at Irvine open data repository has initiated a challenge of sorts to investigate the quality of models of various machine learning methods to build a model for predicting CO and NOx emissions depending on ambient variables and the parameters of the technological process. The novelty and features of this paper are: (i) a contribution to the study of the features of the open dataset on CO and NOx emissions for gas turbines, which will enable one to more objectively compare different machine learning methods for further research; (ii) for the first time for the CO and NOx emissions, a model based on symbolic regression and a genetic algorithm is presented—the advantage of this being the transparency of the influence of factors and the interpretability of the model; (iii) a new classification model based on the symbolic regression model and fuzzy inference system is proposed. The coefficients of determination of the developed models are: R2=0.83 for NOx emissions, R2=0.89 for CO emissions.


  • Open Access

    Preventive Maintenance of the k-out-of-n System with Respect to Cost-Type Criterion

    by Vladimir Rykov, Olga Kochueva, Yaroslav Rykov

    In a previous paper, the problem of how the preventive maintenance organization for the k-out-of-n: F system could be used, in order to maximize system availability, was considered. The current paper continues these investigations using a different optimization criterion. The proposed approach is based on decision making theory for regenerative processes. We propose a general procedure for comparing different preventive maintenance strategies based on the ordered statistics distributions, aiming to choose the best one with respect to cost-type criterion. The lifetime distributions of system units are usually unknown and only one or two of their moments are available. For this reason, we pay special attention to the sensitivity analysis of decision making about preventive maintenance, taking into account the shape of the system unit lifetime distributions. A numerical study of two examples based on a real-world system illustrates the results of the proposed approach.