On the reliability of data analysis in quality control

Kudrya, A. V.; Shtremel, M. A.

doi:10.1007/s11041-010-9279-5

Cited by 5 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can finalize in obtaining the mixed results. E.g., if we determine differences between two series of measurement results (volumes n 1 , and n 2 respectively) for any characteristic, it is usually suggested that "histogram of the process (or product) parameters data should have the form of single-modal dome-shaped curve" [13]. Based on this, significance of the difference [<[> 1 -<[> 2 ] z 0 is usually evaluated by the average values <[> 1 and <[> 2 and their mean-square deviations according to the Student criterion; thereby normal distribution [ is allowed.…”

Section: Statistics Of the Values Of The Process And Product Paramete...mentioning

confidence: 99%

“…Importance of taking into account statistical nature of metallurgical objects has already shown its efficiency in using regression for narrowing space for parameters or application of complicated heuristic techniques of cognitive graphics. They can be used for searching the areas with dominating type of relationship during reveal of interacting deviations of technological parameters, which are related to different technological stages, use of schemes of non-parametric discrimination, not depending on kind of distribution (and more robust thereby) [12,13].…”

Section: Statistics Of the Values Of The Process And Product Paramete...mentioning

confidence: 99%

See 1 more Smart Citation

On necessity of taking into account statistical nature of the objects using Big Data in metallurgy

Kudrya¹,

Sokolovskaya²,

Kodirov³

et al. 2022

cisisr

Self Cite

View full text Add to dashboard Cite

Several statistical restrictions, which are critically important for correct use of different Big Data procedures in metallurgy for attestation and management of quality of metal products are evaluated. Representative production control data stores for steel manufacturing technologies are used as the research object. This research covered wide grade and dimension range of steels: large forgings of heat treatable 38KhN3MFA-Sh steel, rolled products of 40KhMFA steel, sheet 17G1S-U, 09G2S and 15KhSND steels. Possible scale of variety of values distribution both for managing parameters and characteristics of strength, plasticity and toughness is shown using the coefficients of asymmetry and kurtosis. These characteristics are varied within the technological tolerance range. Accompanying risk during metal quality prediction and management, e.g. using the methods of parametric statistics, was evaluated for the case when this circumstance was not taken into account. The features of influence of a sample list volume on the results of statistical processing of large production control data stores and metallurgical product are revealed. It is shown how absence of common space of parameters restricts possibilities of classic statistics in metallurgy, makes non-effective the management "by disturbance" principle. In this connection, possibilities of non-parametric statistics, presented by Kolmogorov -Smirnov criterion, which is not depended on distribution of collection of analyzed sample lists, are evaluated. To provide objective selection of the areas with dominating type of relationship, it is necessary to take into account possibility of existence of different evolution scenarios for structure and defects along the technological chain (technological heredity) within the framework of rather wide tolerance range, as well as features of their appearance. Difference in the evolution mechanisms of structures and defects within the framework of separate technological trajectory is a cause of appearances of developed heterogeneity for nominal single-type structures which have, however, different scales, as well as accompanying quality dispersion (which is often essential). Taking this circumstance into account allows to find out the links in the system "managing parameters -final parameters of metal products", which are not always evident during their search using generally accepted approaches. Development of the complex of rules for online management of metal products quality is possible on this base. Key words: quality management of metal products, retrospective analysis of data bases for production control, Big Data, technological heredity, classic and non-parametric statistics, regression, kind of distribution of parameter values, dominating type of relationship.

show abstract

Section: Statistics Of the Values Of The Process And Product Paramete...mentioning

confidence: 99%

Section: Statistics Of the Values Of The Process And Product Paramete...mentioning

confidence: 99%

On necessity of taking into account statistical nature of the objects using Big Data in metallurgy

Kudrya¹,

Sokolovskaya²,

Kodirov³

et al. 2022

cisisr

Self Cite

View full text Add to dashboard Cite

show abstract

“…This implies the application of another nonlo cal adaptive control logic: when a potential risk is (2) insensitive to the formation of conchoidal fracture. Point x* (where dis tance D* = 0.037) indicates the best division of the remaining heats into such groups [31]. detected in real time, the subsequent operations rather than a disturbing factor are corrected to neutralize its effect.…”

Section: Production Control Data Miningmentioning

confidence: 99%

“…The development of means and methods for con trolling structures and fracture surfaces favors a deep understanding of the physics of phenomena and pro cesses (for the critical technology trajectories calcu lated by statistical methods) and makes it possible to achieve an objective estimate of the metal quality, which increases the reliability of forecasting and the development of control techniques [31].…”

Section: Production Control Data Miningmentioning

confidence: 99%

Information technologies for producing high-quality metal products

Kudrya

Sokolovskaya

2011

Russ. Metall.

Self Cite

View full text Add to dashboard Cite

The creation of the critical promising materials that determine the efficiency of the next generation equipment is based on a combination of material designing means and a quality control information technology in industry. CALS (continuous acquisition and life cycle support) systems are integrated informa tion systems that follow the life cycle of a product and combine the designing and production of objects (CAD/CAM/CAE systems) with the systems of con trolling the manufacture, resources, marketing, sale, maintenance, and repair of products. In the produc tion of a wide spectrum of steel, alloy, and composite material grades and products made of them, CALS cannot operate without a quality control subsystem. There are random local industrial systems of control ling one technological unit. However, the production of materials is characterized by a strong technological heredity: deviations within allowable limits at various states and operations are complexly interrelated [1, 2]. There are no operating "upper level" metasystem (for through control of the entire production string), con trol algorithms adapted for certain technological classes, and proper quality control means and meth ods (in particular, structure quality control system). In particular, the mechanisms of fracture of various structures are incompletely understood, and this is necessary to choose their optimum configurations (with allowance for an inevitable technological heter ogeneity) to provide the required level of properties [1][2][3][4][5].The development of measurement and control means, an increase in the available computational power, CALS algorithms for through control in terms of a direct technology, and modern software packages (i.e., information technologies) provide the possibility of deeper understanding of the nature of strength, ductility, and impact toughness of various materials as the basis for the formation of effective means for con trolling the quality of metal products. If a certain prob lem can be solved using an information technology, this is much cheaper and faster than the traditional approach related to a replacement of equipment and processes. INITIAL INFORMATION ON A TECHNOLOGICAL PROCESSModern metallurgy is characterized by a long pro duction string, the number of operations in which is determined by the purpose of the product. These oper ations are usually characterized by an alloy composi tion; the heat, deoxidation, and casting indices; and the temperatures and reductions in stands or the tem perature-time parameters of forging and heat treat ment (when it is the final technological stage). The parameters measured at every technological operation can be controlled and make up K ≈ 100 parameters of process ξ k (in total, K dimensional vector of ξ param eters) [6]. As a rule, they are recorded in real time, fixed in technological certificates, or are stored in a general electron information archive at an enterprise.The product quality is characterized by ten or more output parameters y i with allowable levels d i (y...

show abstract