Контрольні карти в статистичних методах аналізу та синтезу автоматичних систем регулювання
Анотація
CONTROL CARDS IN THE STATISTICAL ANALYSIS AND SYNTHESIS METHODS OF AUTOMATED CONTROL SYSTEMS
L. Vlasenko, A. Ladanyuk
Most modern automatic control systems, installed in the factories of the food industry based on the use of standard regulators. The main drawbacks of such systems are the relative nercinskij, a delay in the regulatory process, the need for parametric, and sometimes even structural adjustment of the control device via the change of external and internal disturbances acting on the controlled system. In conditions of high competition and rapid technical development to improve the efficiency of technological systems of food production are actively implementing multidimensional optimal controllers, neural network controllers, scenario approaches, cognitive maps and methods of synergetics and the like. Feature of the application of the above approaches is required to develop an adequate mathematical model of the control object, that is usually associated with a large number of problems ranging from significant constraints on its output, the possibility of organizing a passive or active experiment and ending with the difficulty of identifying dependencies between the parameters.
The use of statistical methods in management significantly increases its efficiency, because it does not require prior and mandatory withdrawal and use of mathematical models and provides a rapid assessment of the state of the system quick and correct response to the situation that has developed.
The purpose – increase of efficiency of functioning of automatic control system by the use of methods of statistical diagnosis.
Methods. The example of the processing of numeric data and operation of the evaporator plant of a sugar factory shows the identification of problems of technological process at early stages using different types of control charts.
Results. In practice, most violations of the normal course of technological processes are operators with a simple visual observation. The success of the regulation thus depends on its experience, qualifications, and how faithfully he performs his job. It is necessary to consider a number of problems:
the operator needs to react to changes of a large volume of operational information;
detection of violations the operator carries out haphazard, often intuitive, sometimes accidentally;
as the operator identificeret violations based on his previous experience, he can identify the problem on time or even pay her attention too late if this situation is new or unknown;
through the monotony and boredom of work, the attention of the operator is reduced, which may lead to a delayed response to the occurrence of the violation;
usually the operator is guided by its own set of characteristics which determines the occurrence of a dangerous situation and which incite him to action;
the main goal of the operator in the event of violation sees in prejudice reduction of production, and not online identifying and addressing "problem" areas;
there is a complexity regarding the operational definition of the situation that has developed, as problems or temporary release;
whatever the qualifications of the operator, it without special methods and calculations cannot detect the appearance of Rosegarden technological process at early stages.
To eliminate the aforementioned disadvantages and facilitate the work of decision-makers, it is advisable to use a subsystem of the decision support built on statistical methods. In particular, the statistical control of the management of technological processes ensures the timely introduction of corrective action: change the parameters or the structure of the regulating device. The control cards provide the speed signal changes in the process, allow us to estimate the amount of change in controlled variable and the frequency of such cases, is the basis for the introduction of corrective actions taking into account constraints on the decision time. Control charts are graphic tools of analysis that are easily interpreted and are built in a production environment in real time. Also, the advantages of using control charts should include provided visual observation of a controlled variable and changes in the technological process at early stages.
Analysis of the quality of the technological process, obeys the normal distribution law, can be carried out using one-dimensional maps for the independent variables and multivariate – correlated. Univariate control charts of Suharto gained its popularity because of the ease of construction and interpretation, detecting operational emissions. Their feature is the simultaneous analysis are located on the same map sheet, designed to control the quantitative trait for the average X and maps the range R. For example, the span describes the rate of change of the controlled variable, the emission on the R-map, in the absence of X-the map indicates that a problem occurred long before the appearance of the alarm signal analysis, the change of medium X.
For example, the process of controlling the temperature of the boiling syrup to the evaporator plant sugar factory. The control card is built with the help of STATISTICA software product.
To assess the adequacy of the obtained result were constructed and analysed an integrated schedule containing the Shewhart charts, based on maximum tolerances stipulated by the technical regulations, and indicators of validity.
The work shows the feasibility and benefits of using univariate Shewhart charts for detecting process variance in the early stages for the subsequent introduction of corrective actions. Performance evaluation of fitness demonstrates the adequacy of the results recorded on checklists. So, proper addition of automatic control system cards Shewhart given the fact that they only signal the occurrence of alarm, but do not indicate the exact place of its origin, will improve the efficiency of technological complex.
Посилання
Lutskaya, N. M., Vlasenko, L. O. (2013). Rozrobka bagatovimirnih optimalnih regulyatoriv dlya viparnoyi stancii cukrovogo virobnictva, scho funkcionue v umovah intervalnoi neviznachenosti [Development of multidimensional optimal controllers for sugarmill evaporation plant which operates in interval indetermination conditions]. Scientific works of National University of food technologies, 52, 48–61.
Klyachkin, V. N., Safin, V. A., Sagdeeva U. K., Sidyakina A. A. (2010). Progammnoe obespechenie mnogomernogo statisticheskogo kontrolya processa s uchotom pogreshnostey izmereniy [Software multivariate statistical process monitoring with consideration of measurement errors]. Computer science: collection of scientific works / under. edited by V. N. Negoda, 648–652.
Garcia-Diaz, A. C. (2007). The effective variance control chart for monitoring the dispersion process with missing data. European J. Industrial Engineering, 1, 1.
Klyachkin, V. N., Safin, V. A. (2011). Upavlenie kachestvom produkcii na osnove sovershenstvovaniya metodov mnogomernogo statisticheskogo kontrolya processov [Product quality management on the basis of perfection of methods of the multivariate statistical control of processes]. Proceedings of the Samara scientific center by Russian Academy of Sciences, 4 (2), 537–542.
Himmelblau, D. (1983). Obnarugenie i diagnostica nepoladok v himicheskih i neftehimicheskih processah [Fault detection and diagnosis in chemical and petrochemical processes]. Leningrad, Chemical, 352.
Ladanyuk, А., Zaec, N., Vlasenko L. (2016). Suchasni tehnologii konstruyuvannya system avtomatizacii skladnih system (meregevi strukturi, adaptacija, diagnostika ta prognozuvannya: monografija [Modern technologies of designing of systems of automation of complex objects (network structure, adaptation, diagnostics and forecasting): the monograph]. Kiev, Lira-K, 312.
Vlasenko, L., Ladanyuk, A., Sich, M. (2014). [Statistical diagnostics of operating process of sugar factory evaporator plant]. Automation of technological and business processes, 2 (18), 50–60.
Statsoft [Electronic resource]. Available at: http://www.statsoft.ru.
Завантаження
Опубліковано
Номер
Розділ
Ліцензія
Стосунки між правовласниками і користувачами регулюються на умовах ліцензії Creative Commons Із Зазначенням Авторства – Некомерційна – Поширення На Тих Самих Умовах 4.0 Міжнародна (CC BY-NC-SA 4.0):https://creativecommons.org/licenses/by-nc-sa/4.0/deed.uk
Автори, які публікуються у цьому журналі, погоджуються з наступними умовами:
- Автори залишають за собою право на авторство своєї роботи та передають журналу право першої публікації цієї роботи на умовах ліцензії Creative Commons Attribution License, котра дозволяє іншим особам вільно розповсюджувати опубліковану роботу з обов'язковим посиланням на авторів оригінальної роботи та першу публікацію роботи у цьому журналі.
- Автори мають право укладати самостійні додаткові угоди щодо неексклюзивного розповсюдження роботи у тому вигляді, в якому вона була опублікована цим журналом (наприклад, розміщувати роботу в електронному сховищі установи або публікувати у складі монографії), за умови збереження посилання на першу публікацію роботи у цьому журналі.
- Політика журналу дозволяє і заохочує розміщення авторами в мережі Інтернет (наприклад, у сховищах установ або на особистих веб-сайтах) рукопису роботи, як до подання цього рукопису до редакції, так і під час його редакційного опрацювання, оскільки це сприяє виникненню продуктивної наукової дискусії та позитивно позначається на оперативності та динаміці цитування опублікованої роботи (див.The Effect of Open Access).