Albo, Janelle Ann C.  <br/><br/>
Vibration Analysis Of College Of Engineering (Coe) Building At The Technological University Of The Philippines – Manila Using Raspberry Shake 4d And Artificial Neural Network/ 
Janelle Ann C. Albo, Jonna P. Coronacion, Mark Aldrin I. Gutierrez, Liezel B. Nuñez and Lea Jelizabeth T. Pico.-- 
 - Technological University of the Philippines, Manila. 
 - xv, 173 pages.  29 cm 
<br/><br/> Bachelor's thesis 
<br/><br/>College of Engineering.-- 
<br/><br/>Includes bibliographic references and index. 
<br/><br/> The Structural Health Monitoring (SHM) systems have become essential<br/>instruments in the field of civil engineering, significantly improving the efficiency,<br/>safety, and dependability of structures. With the use of sensors, it would be possible to<br/>continuously monitor the structural integrity of buildings and systems throughout the<br/>duration of their service life. This would enable early detection of structural damage<br/>based on predicted structural responses. The study would involve gathering and analyzing<br/>seismic data from Raspberry Shake 4D (RS4D) to comprehend the College of<br/>Engineering (COE) Building's dynamic behavior, training machine learning models to<br/>predict acceleration response of the fifth-floor sensor and detect structural vulnerabilities<br/>and validating the methodology through comparative analysis with traditional structural<br/>assessment methods. The theoretical period obtained from FEM was 0.8560 seconds on<br/>mode 1 on 1.168 hertz with 74.42% of mass participation factor while the actual period<br/>of the COE building falls under mode 3 which on 0.6250 seconds on 1.60 hertz with 3.00<br/>% mass participation factor based on the Ansys Software. This means that with March to<br/>May,seismic activity does not excite the building for it is not close to the resonance period<br/>of COE. Machine learning algorithm percentage of accuracy falls on 88.02% after<br/>simulation and having an overall R-value= 0.82297. This indicates that the model created<br/>in Machine Learning performs strong positive correlation from the predicted to the actual<br/>response and it can be said working well and ready for future usage. The study would<br/>improve the structural resilience and safety measures of COE Building for future<br/>infrastructure assessments and risk mitigation. 
<br/><br/><label>Subjects--Topical Terms: </label><br/>Civil Engineering<br/>Structural Health Monitoring
<br/><br/><label>LC Class. No.: </label>BTH TA 145  / A43 2024