Pengendalian Kualitas Air PDAM Delta Tirta Kabupaten Sidoarjo Menggunakan Peta Kendali Vector Autoregressive-Based Maximum MCUSUM (VAR-Based MAX-MCUSUM)

Alim, Elvina Khoirunisa (2026) Pengendalian Kualitas Air PDAM Delta Tirta Kabupaten Sidoarjo Menggunakan Peta Kendali Vector Autoregressive-Based Maximum MCUSUM (VAR-Based MAX-MCUSUM). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5002221056-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (5MB) | Request a copy

Abstract

Air bersih merupakan kebutuhan dasar yang ketersediaannya sangat penting, termasuk di Kabupaten Sidoarjo yang memiliki pertumbuhan penduduk dan industri yang pesat. Untuk memenuhi kebutuhan tersebut, PDAM Delta Tirta Kabupaten Sidoarjo berperan sebagai penyedia layanan air bersih yang harus senantiasa memantau kualitas produksinya berdasarkan beberapa parameter kualitas, di antaranya kekeruhan, pH, dan sisa klor. Ketiga parameter tersebut saling berkorelasi dan mengandung autokorelasi akibat proses produksi yang berlangsung secara kontinu, sehingga dibutuhkan metode pengendalian kualitas yang mampu mengatasi masalah autokorelasi, salah satunya yaitu peta kendali \textit{Vector Autoregressive-Based} \textit{Maximum} MCUSUM (VAR-Based Max-MCUSUM). Metode ini bekerja dengan memodelkan data menggunakan VAR untuk memperoleh residual yang bebas autokorelasi, kemudian residual tersebut dipantau mengunakan peta kendali Max-MCUSUM. Berdasarkan pemodelan VAR yang dilakukan, terpilih model VAR(7) dengan asumsi residualnya sudah memenuhi asumsi \textit{white noise} dan berdistribusi normal multivariat. Selanjutnya, pemantauan Fase I dengan peta kendali VAR-\textit{Based} Max-MCUSUM menunjukkan bahwa proses terkendali secara statistik dengan target ARL 370 dan batas kendali atas 20.3616. Namun, pada Fase II, terdeteksi kondisi \textit{ out of control} mulai pengamatan ke-33 yang disebabkan oleh tingginya fluktuasi sisa klor. Hasil analisis kapabilitas proses multivariat ($MP_{pk}$) sebesar 0.9491 juga mengindikasikan bahwa proses produksi air belum sepenuhnya kapabel dan berisiko tidak memenuhi standar baku mutu kesehatan yang berlaku.
=======================================================================================================================================
Clean water is a basic necessity whose availability is highly important, including in Sidoarjo Regency, which has rapid population and industrial growth. To meet this demand, PDAM Delta Tirta Kabupaten Sidoarjo serves as a clean water service provider that must continuously monitor the quality of its production based on several quality parameters, including turbidity, pH, and residual chlorine. These three parameters are correlated and exhibit autocorrelation due to the continuous nature of the production process, requiring a quality control method capable of addressing autocorrelation, one of which is the \textit{Vector Autoregressive-Based} \textit{Maximum} MCUSUM (VAR-Based Max-MCUSUM) control chart. This method works by modeling the data using VAR to obtain autocorrelation-free residuals, which are then monitored using the Max-MCUSUM control chart. Based on the VAR modeling, the VAR(7) model was selected because its residuals satisfy the \textit{white noise} assumption and follow a multivariate normal distribution. Furthermore, Phase I monitoring using the VAR-\textit{Based} Max-MCUSUM control chart shows that the process is statistically in control, with a target ARL of 370 and an upper control limit of 20.3616. However, in Phase II, an \textit{out of control} condition is detected starting at the 33rd observation due to high fluctuations in residual chlorine. The multivariate process capability analysis result ($MP_{pk}$) of 0.9491 also indicates that the water production process is not yet fully capable and carries the risk of failing to meet the applicable health quality standards.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Autokorelasi, Kapabilitas Proses, Max-MCUSUM, Pengendalian Kualitas, VAR, Autocorrelation, Process Capability, Quality Control
Subjects:	Q Science Q Science > QA Mathematics Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Elvina Khoirunisa Alim
Date Deposited:	27 Jul 2026 08:09
Last Modified:	27 Jul 2026 08:09
URI:	http://repository.its.ac.id/id/eprint/138126

Actions (login required)

View Item