Development of Slope Failure Prediction Interval Model Based on Inverse Velocity

2020 ◽  
Vol 1 (1) ◽  
pp. 525-532
Author(s):  
Maria Christine Rosaria ◽  
Rania Salsabila ◽  
Muhammad Khalif Arda ◽  
Fery Andika Cahyo ◽  
Rachmat Hamid Musa

ABSTRACT Provided with accurate and quasi real time deformation data, there are at least 2 methods that can be utilized to predict a slope failure. Inverse velocity method, coined by Fukuzono, aims at the interception of inverse velocity line to zero value at X time axis as the prediction of slope failure. More recent method called SLO, develop by Mufundirwa, puts emphasize on interception of acceleration regression line with X velocity axis. This paper is intended first and foremost to establish well-structured comparison between the two aforementioned methods. By using the same set of displacement data that show progressive deformation trend from Slope Stability radar, both SLO & Inverse Velocity method will be put into trial. Not only the accuracy of the failure prediction time, but also the comparison between the R2 attribute will be examine to reveal which method that yield better data statistically. One of the selected study case, from several which is presented on the paper, reveal that SLO method give failure prediction closer with the actual failure compared to Inverse Velocity method. The actual failure is happening at 21:59 AM January 1st 2016. SLO method generates failure prediction 10 minutes prior the actual failure, while Inverse Velocity generates failure prediction plus 68 minutes after the failure. R2 value for SLO method and Inverse Velocity method respectively are 0.710 & 0.630. Apart from this results comparison, a more in depth examination toward the nature of both methods delivers pro & con of each method. SLO method seems more accurate but having a constraint in which if there are no previous database of maximum velocity during collapse, prediction is almost impossible to make. Inverse Velocity method could address this flaw by projecting the inverse velocity line to zero value for the very least. Further explanation about the flaw and advantages of both methods will be conveyed in more detail on the later part of this paper.   Key words: Failure Prediction, SLO, Inverse Velocity, SSR  ABSTRAK Dengan adanya pengambilan data deformasi yang akurat dan mendekati “real time”, terdapat setidaknya dua metode yang dapat digunakan untuk memprediksi longsor. Metode inverse velocity, yang dikembangkan oleh Fukuzono, adalah metode yang menggunakan perpotongan grafik inverse velocity dengan titik nol sebagai acuan atau nilai dari prediksi longsor. Metode lain yang lebih baru dibandingkan metode inverse velocity adalah metode SLO yang dikembangkan oleh Mufundirwa. Metode ini lebih ditekankan pada perpotongan antara grafik akselerasi dengan nilai kecepatan pada sumbu X. Tujuan utama dari paper ini adalah penyajian perbandingan yang terstruktur antara kedua metode tersebut. Penelitian terhadap metode SLO dan inverse velocity menggunakan data deformasi progresif yang sama dari Slope Stability Radar. Tidak hanya keakuratan prediksi waktu longsor, tetapi perbandingan nilai R2 pun akan menentukan metode yang lebih efektif secara statistik. Pada salah satu studi kasus, dari beberapa kasus yang dibahas di paper ini, menunjukkan bahwa metode SLO memberikan prediksi waktu longsor yang lebih mendekati waktu longsor yang sebenarnya jika dibandingkan dengan metode inverse velocity. Longsor yang sebenarnya terjadi pada tanggal 1 Januari 2016, pukul 21:59. Metode SLO menghasilkan prediksi longsor 10 menit lebih awal dari waktu longsor yang sebenarnya, dimana metode inverse menghasilkan prediksi longsor 68 menit setelah waktu longsor. Nilai R2 untuk metode SLO dan inverse velocity adalah 0.71 dan 0.63. Di samping perbandingan kedua hasil di atas, pemahaman lebih mendalam tentang sumber dari kedua metode tersebut memunculkan hasil plus dan minus dari masing-masing metode. Metode SLO memang terlihat lebih akurat namun metode ini membutuhkan data kecepatan maksimal saat kejadian longsor sebelumnya. Jika tidak ada, maka prediksi hampir tidak mungkin untuk dibuat. Sebaliknya, kelemahan tersebut tidak terdapat pada metode inverse velocity karena dapat diproyeksikan pada titik nol. Penjelasan lebih dalam mengenai kelebihan dan kekurangan dari kedua metode tersebut akan dibahas selanjutnya pada paper ini. Kata kunci: Prediksi longsor, SLO, Inverse velocity, SSR


2013 ◽  
Vol 133 (9) ◽  
pp. 278-283 ◽  
Author(s):  
Masato Futagawa ◽  
Mitsuru Komatsu ◽  
Hikofumi Suzuki ◽  
Yuji Takeshita ◽  
Yasushi Fuwa ◽  
...  

2015 ◽  
pp. 1193-1197
Author(s):  
Li-Dong Wang ◽  
Qing Gao ◽  
Xian-Quan Luo ◽  
Guan-Hui Liang

1992 ◽  
pp. 11-20
Author(s):  
Hiroyoshi KASA ◽  
Hirohito KOJIMA ◽  
Shigeyuki OBAYASHI ◽  
Masahiro KURODAI

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
G. Ramkumar ◽  
Satyajeet Sahoo ◽  
T. M. Amirthalakshmi ◽  
S. Ramesh ◽  
R. Thandaiah Prabu ◽  
...  

Solar energy conversion efficiency has improved by the advancement technology of photovoltaic (PV) and the involvement of administrations worldwide. However, environmental conditions influence PV power output, resulting in randomness and intermittency. These characteristics may be harmful to the power scheme. As a conclusion, precise and timely power forecast information is essential for the power networks to engage solar energy. To lessen the negative impact of PV electricity usage, the offered short-term solar photovoltaic (PV) power estimate design is based on an online sequential extreme learning machine with a forgetting mechanism (FOS-ELM) under this study. This approach can replace existing knowledge with new information on a continuous basis. The variance of model uncertainty is computed in the first stage by using a learning algorithm to provide predictable PV power estimations. Stage two entails creating a one-of-a-kind PI based on cost function to enhance the ELM limitations and quantify noise uncertainty in respect of variance. As per findings, this approach does have the benefits of short training duration and better reliability. This technique can assist the energy dispatching unit list producing strategies while also providing temporal and spatial compensation and integrated power regulation, which are crucial for the stability and security of energy systems and also their continuous optimization.


Sign in / Sign up

Export Citation Format

Share Document