Ta'lim innovatsiyasi va integratsiyasi

KIMYOVIY JARAYONNING NOTO'G'RI DIAGNOSTIKASI UCHUN JARAYON TOPOLOGIYASI KONVOLYUTSION TARMOQ MODELI.

Muborak Abduqodirova

Durbek Mambetov

Shoxida Jumanova

Javohirbek Mahmudov

Keywords: Kalit so῾zlar: Nosozlik diagnostikasi, kimyoviy jarayoni, jarayon topologiyasi bilan konvolyutsion tarmoq, tushuntiriladigan chuqur o'rganish, jarayon xavfsizligi.

---

Abstract

Annotatsiya. Kimyoviy jarayonlarda har doim potentsial xavfsizlik xavfi
mavjud. Jarayonlarning anormalliklari yoki nosozliklari kutilmagan hayot va mulkni
yo'qotish bilan og'ir baxtsiz hodisalarga olib kelishi mumkin. Erta va aniq nosozliklarni
aniqlash va tashxislash (FDD) bu baxtsiz hodisalarning oldini olish uchun juda
muhimdir. Jarayondagi nosozliklarni aniqlash uchun ma'lumotlarga asoslangan ko'plab
FDD modellari ishlab chiqilgan. Biroq, modellarning aksariyati yomon tushuntirishga
ega qora quti modellari. Ushbu maqolada murakkab kimyoviy jarayonlarning xato
diagnostikasi uchun jarayon topologiyasi konvolyutsion tarmoq (PTCN) modeli taklif
etiladi. Benchmark Tennessee Eastman jarayoni bo'yicha o'tkazilgan tajribalar shuni
ko'rsatdiki, PTCN tarmoq tuzilmasi soddalashtirilgan va o'quv ma'lumotlari va
hisoblash resurslari miqdoriga kamroq tayangan holda nosozliklarni tashxislash
aniqligini yaxshilagan. Shu bilan birga, modelni yaratish jarayoni ancha oqilona bo'ladi
va modelning o'zi ancha tushunarli bo'ladi.

---

References

Adabiyotlar:

Amin, M.T., Khan, F., Ahmed, S., Imtiaz, S., 2020. A novel data-driven

methodology for fault detection and dynamic risk assessment.

Can.J.Chem.Eng.98,2397–2416, http://dx.doi.org/10.1002/cjce.23760.

Arunthavanathan, R., Khan, F., Ahmed, S., Imtiaz, S., 2020a. An

analysis of process fault diagnosis methods from safety perspectives.

Comput.Chem.Eng.,http://dx.doi.org/10.1016/j.compchemeng.2020.10

, 107197.

Arunthavanathan, R., Khan, F., Ahmed, S., Imtiaz, S., Rusli, R.,

b. Fault detec- tion and diagnosis in process system using artificial

intelligence-based cognitive technique. Comput. Chem. Eng. 134,

http://dx.doi.org/10.1016/j.compchemeng. 2019.106697, 106697.

Bathelt, A., Ricker, N.L., Jelali, M., 2015. Revision of the Tennessee

eastman process model. IFACPapersOnLine 48, 309–314,

http://dx.doi.org/10.1016/j.ifacol.2015.08.199.

Bikmukhametov, T., Jäschke, J., 2020. Combining machine learning

and process engineering physics towards enhanced accuracy and

explainability of data- driven models. Comput. Chem. Eng. 138,

, http://dx.doi.org/10.1016/j. compchemeng.2020.106834.

Khan, F., Rathnayaka, S., Ahmed, S., 2015. Methods and models in

process safety and risk management: past, present and future.

Process.Saf.Environ.Prot.98,116–147,

http://dx.doi.org/10.1016/j.psep.2015.07.005.