Method of Statistical Spline Functions for Solving Problems of Data Approximation and Prediction of Objects State

Babak, Serhiy; Babak, Vitalij; Zaporozhets, Artur; Sverdlova, Anastasia

doi:10.2139/ssrn.3734104

Cited by 5 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To determine the values of the corresponding coefficients, the decomposition characteristic of information signals describing the various defects of the samples under study, it is necessary to obtain a function that approximates the distribution of the values of each of the spectral decomposition coefficients depending on the degree of damage (defectiveness) of the sample under study [19]. Such a function can be determined by interpolating known values of decomposition coefficients, for example, by power polynomials or splines [5]. Further, for each spectral component, it is necessary to select the desired damage degree (defect size) x of the controlled area, determine the value of the spectral components by the established functional dependencies and perform the inverse transformation.…”

Section: Construction and Study Of Approximation Equationsmentioning

confidence: 99%

“…First, the existence of such model allows you to build a library of information signals that characterize possible defects in composites and therefore can be used to train and configure the information and diagnostic system as a whole or in a particular case of a neural network classifier without physically manufacturing such samples [4]. Secondly, a simulation model of the information signal can be used to verify the accuracy of diagnosis and classification, justify the choice of the most successful architecture and type of neural network classifier, select the threshold sensitivity of the system, validate the information and diagnostic system and, if necessary, adjust its parameters, etc [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Method of Reference Signals Creating in Non-Destructive Testing Based on Low-Speed Impact

2021

View full text Add to dashboard Cite

The article describes the approach to the formation of a simulation model of information signals, which are typical for objects with different types of defects. The dispersive analysis of the signal spectrum components in the bases of the discrete Hartley transform and the discrete cosine transform is carried out. The analysis of the form of the reconstructed information signal is carried out depending on the number of coefficients of the spectral alignment in Hartley bases and cosine functions. The basis of orthogonal functions of a discrete argument is obtained, which can be used for the spectral transformation of information signals of a flaw detector. A method of simulation of information signals has been developed and experimentally investigated, which allows taking into account the deterministic and random components of the characteristics of real information signals. References 24, figures 13, tables 3.

show abstract

Section: Construction and Study Of Approximation Equationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Method of Reference Signals Creating in Non-Destructive Testing Based on Low-Speed Impact

2021

View full text Add to dashboard Cite

show abstract

“…are equipped with automated control systems for technological parameters [5][6][7]. The controlled parameters, in addition to information about the flow of technological processes, also contains information about the current state of the equipment, the appearance and development of various faults [8][9][10]. Analysis of changes in these parameters, performed after accidents, unscheduled equipment stops, usually shows that there were signs of malfunctions that caused the accident or stop, long before the incident [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Predicting anomaly conditions of energy equipment using neural networks

Sverdlova

Zaporozhets

2021

E3S Web Conf.

Self Cite

View full text Add to dashboard Cite

In modern conditions for complex thermal power facilities, the issue of developing methods for predicting equipment failures is especially relevant. Methods based on the intellectualization of diagnostic systems and allowing to obtain predictive models based on the use of both current data received in real time from measuring equipment and retrospective information are considered promising. Intellectualization of the system in terms of the ability to learn allows to quickly adjust the parameters of forecasting models under changing conditions of equipment operation, to determine new deadlines for scheduled repairs and minimize equipment downtime. A limitation of the use of methods is the incompleteness of failure statistics, ie when equipment failures are rare or non-existent. Such diagnostics of energy equipment, especially thermal power facilities, contributes to a more environmentally friendly production.

show abstract