000			02916ntm a2200337 i 4500
003			MY-KuUP
005			20260714172102.0
006			t|||||r|||| 000 0
007			ta
008			260714t20252025my a|||fr|||| 000 0 eng d
020			_aTHE0010730 (Local) _qHardback
040			_aUMPSA _beng _cUMPSA _erda
090			_aFTKKP .K39 2025 r Bc.
100	0		_aKawsalya Pillay A/P Subramaniam, , , _eauthor.
245	1	0	_aOptimizing risk management strategies for pharmaceutical water systems through enhanced intergration of machine learning and quantitative risk assessment / _cKawsalya Pillay A/P Subramaniam
264		1	_aKuantan, Pahang : _bUMPSA, _c2025
264		4	_c© 2025
300			_axi, 47 pages : _billustrations ;
336			_2rdacontent _atext
337			_2rdamedia _aunmediated
338			_2rdacarrier _avolume
347			_2rda _atext file _bPDF
500			_aFaculty of Chemical and Process Engineering Technology
502			_aFinal Year Report (Bachelor of Manufacturing Engineering Technology (Pharmaceuticals) with Hons ) -- Universiti Malaysia Pahang Al-Sultan Abdullah - 2025
504			_aInclude bibliographical reference
520	3		_aPharmaceutical water systems play a crucial role in ensuring the quality and safety of pharmaceutical products. However, contamination risks and system failures remain significant challenges. This study aims to optimize risk management strategies in pharmaceutical water systems through the enhanced integration of machine learning and quantitative risk assessment (QRA). By adopting this approach, a mathematical model was developed to assess membrane fouling risks in reverse osmosis (RO) systems. The Friday 13th (Fr 13) risk assessment framework was utilized to conduct an in-depth evaluation of potential failures in the RO system. Simulations were performed using @RISK software to identify critical parameters influencing system performance. The obtained data was then validated using Scilab, where machine learning techniques were employed to improve the accuracy of risk predictions. Findings from the study indicate that integrating machine learning with QRA enables more proactive risk monitoring and effective failure management. The developed model allows for more precise assessment of membrane fouling failure probabilities and proposes preventive measures to mitigate risks. This research demonstrates that data-driven analytical approaches enhance the resilience of pharmaceutical water systems against contamination risks and failures. The implications of this study contribute to the improvement of risk management efficiency in the pharmaceutical industry, ensuring compliance with global safety and quality standards.
610	2	0	_aFaculty of Chemical and Process Engineering Technology _xDissertations
650		0	_aUniversities and colleges _xDissertations
650		0	_aTheses _xDissertations
942			_2lcc _cPSM
999			_c105216 _d105222