The Use of Regression and Neural Network Modelling in Production Monitoring of an Industrial Enterprise

Regression and neural network model for predicting the required dose of coagulant, depending on the quality of river water supplied for water treatment, are considered, their comparative analysis is carried out. For modelling and forecasting, statistical data collected for the period from 2005 to nowadays. Regression models were built on the true values of the factors (water quality indicators) and on their first differences to eliminate the trend in the series. For the models built on the true values, the statistical significance, was confirmed, high values of the coefficient of the determination were obtained, the values of the approximation errors were 22–25 %. In neural network modelling, networks of the multilayer perception were used. Generalization error on the test set when using other type of networks (RBF-networks, Elman networks), was significant above. Computational experiments have shown that, in general, the accuracy of neural network models is higher than regression ones. The average learning error was 7–9 %, the error on the test set increases to 12–16 %. The reliability of the forecast is increased by training the network on more recent data and using a larger set of facts. An increase in the influence of indicators of permanganate oxidability and colour of the initial river water on the dose of reagents with a simultaneous decrease in the degree of influence of alkalinity over the last five-year period was revealed. This confirms the need to periodically update data for building models. Selected models recommended for implementation in industrial monitoring of water treatment technology at the enterprise.

1. Киекбаев Р.И. Мониторинг качества воды и разработка инженерных решений по повышению барьерной роли сооружений водоподготовки: дисс…. канд. техн. наук. Уфа, Уфимский государственный нефтяной технический университет, 2007. 230 с.

2. Педан В.В. Анализ структуры временных рядов весенних максимальных уровней природных вод. Водные ресурсы. 2003. Т. 30. № 6. С. 688—695.

3. Veresmarty C.J., McIntyre P.B., Gessner M.O., et.al. Global threats to human water security and river biodiversity. Nature. 2010. № 467. P. 15—19.

4. Linnik P.N., Vasylehuk Т.О., Osypenko V.P., Zubko A.V. Влияние гуминовых субстанций на загрязнение водных сред. Impact of humic substances on the secondary pollution of an aquatic environment by heavy metals and some organic compounds caused by the bottom sediments. Pol. J. Che.m. 2008. Vol. 82. No 1—2. C. 411—418.

5. Журба М.Г., Говорова Ж.М. Интенсификация технологий очистки природных вод. Питьевая вода. 2005. № 1. C. 2—5.

6. Холова А.Р., Вагнер Е.В., Вождаева М.Ю., Кантор Е.А., Труханова Н.В., Мельницкий И.А. Результаты экологического мониторинга ограниченно-летучих органических соединений различной природы в воде р. Уфы за период 2000-2014 гг. Матер. Всерос. научной конф. "Мониторинг состояния и загрязнения окружающей среды. Основные результаты и пути развития". Москва, 20—22 марта 2017 г. https://elibrary.ru/item.asp?id=29401426. М., ФГБУ "ИГКЭ Росгидромета и РАН". 2017. С. 60—64.

7. Кантор Л.И., Шемагонова Е.В. Анализ временных рядов загрязнения бенз(а)пиреном воды в р. Уфе. Водные ресурсы. 2002. № 6. С. 743—752.

8. Uyguner C.S., Suphandag S.A., Kerc A., Bekbolet M. Evaluation of adsorption and coagulation characteristics of humic acids preceded by alternative advanced oxidation techniques. Desalination. 2007. Vol. 210. P. 183—193.

9. Долгоносов Б.М., Корчагин К.А. Моделирование изменчивости показателей солевого состава речной воды. Водные ресурсы. 2011. Т. 38. № 3. C. 345—358.

10. Muthulakshmi L., Ramu A., Kannan.N., Murugan A. Application Of Correlation And Regression Analysis In Assessing Ground Water Quality. International Journal of ChemTech Research. 2013. Vol. 5. No. 1. P. 353—361.

11. Nikolaou A.D., Golfinopoulous S.K., Arhonditsis G.B., Kolovoyiannis V., Lekkas T.D. Modeling the formation of chlorination by-products in river water with different quality. Chemosphere. 2004. Vol. 55. P. 409—420.

12. Барский А.Б. Нейронные сети: распознавание, управление, принятие решений М., Финансы и статистика, 2004. 176 c.

13. Ки Дж.У. (Key J.W.) Искусственные нейронные сети управления технологическими процессами. Часть 2. Control Engineering. 2016. Vol. 64. No 4. P. 106—110.

14. Egorov A.F., Savitskaya T.V., Levushkina S.A., Levushkin A.S. Intelligent Decision Support System for Controlling the Atmospheric Air Quality. Theoretical Foundations of Chemical Engineering. 2010. Vol. 44. No. 5. P. 822—828.

15. Эконометрика. Учебник. Под ред. И.И. Елисеевой. М., Проспект, 2011. 288 с.