Safitriani, Nur Rezky (2023) Diagram Kontrol Multivariat Fuzzy T^2 Hotelling Dengan α_cut Menggunakan Trapezoidal Fuzzy Number (TrFN) Beserta Aplikasinya. Masters thesis, Institut Teknologi Sepuluh Nopember.
Text
6003211016-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2025. Download (4MB) | Request a copy |
Abstract
Kualitas suatu produk merupakan faktor terpenting dalam industri manufaktur yang dapat dipertahankan melalui Statistical Process Control (SPC), salah satunya diagram kontrol. Pengontrolan kualitas produk atas dua atau lebih karakteristik kualitas yang berkorelasi lebih efisien menggunakan diagram kontrol multivariat. Namun, kualitas produk ada yang tidak dapat diukur sehingga diperlukan penilaian dalam kriteria linguistik yang dapat menyebabkan ambiguitas. Hal ini dapat diatasi menggunakan teori himpunan fuzzy sehingga menjadi diagram kontrol fuzzy multivariat, salah satunya fuzzy T^2 Hotelling. Metode ini sensitif terhadap pergeseran mean tetapi tidak sensitif pergeseran mean yang kecil sehingga ditambahkan α_cut sekaligus untuk menyelidiki keketatan pemeriksaan. Statistik fuzzy T^2 Hotelling didasarkan pada nilai representatif melalui fungsi keanggotaan dimana Triangular Fuzzy Number (TFN) yang telah digunakan memiliki pengembangan yakni Trapezoidal Fuzzy Number (TrFN). Penelitian ini mengembangkan diagram kontrol multivariat fuzzy T^2 Hotelling dengan α_cut menggunakan TrFN dan evaluasi kinerja dengan pendekatan ARL beserta aplikasinya pada industri bahan bangunan di UD Tiga Beton sebagai penghasil batako press. Pembuatan diagram kontrol ini diawali dengan pembentukan matriks fungsi keanggotaan dari representasi kurva trapesium hingga perhitungan nilai statistik dan membuat plotnya. Hasil evaluasi kinerja diagram kontrol ini menggunakan TrFN dan TFN telah sensitif terhadap pergeseran mean yang kecil yang ditandai dengan adanya penurunan nilai ARL. Selain itu, pada penggunaan TrFN menunjukkan semakin besar nilai α_cut yakni sebesar 0,9 maka semakin baik performa dalam mengontrol kualitas dalam pergeseran kecil, sedangkan penggunaan TFN menunjukkan performa yang sama dalam mengontrol kualitas dalam pergeseran kecil dengan nilai α_cut yang berbeda. Pada penerapannya, diagram kontrol multivariat fuzzy T^2 Hotelling dengan α_cut sebesar 0,9 menggunakan TFN lebih sensitif dalam mendeteksi pengamatan yang tidak terkendali pada produksi batako press di UD Tiga Beton walaupun hanya terdapat sedikit perbedaan dengan menggunakan TrFN simetris.
======================================================================================================================================
The quality of a product is the most important factor in the manufacturing industry which can be maintained through Statistical Process Control (SPC), one of which is a control chart. Product quality control over two or more correlated quality characteristics is more efficient using a multivariate control chart. However, there is product quality that cannot be measured, so an assessment is needed in linguistic criteria which can cause ambiguity. This can be overcome using fuzzy set theory so that it becomes a multivariate fuzzy control chart, one of which is the fuzzy T^2 Hotelling. This method is sensitive to mean shifts but not sensitive to small mean shifts, so α_cut is added at once to investigate the tightness of the check. the fuzzy T^2 Hotelling statistics are based on representative values through membership functions where the Triangular Fuzzy Number (TFN) that has been used has a development, namely the Trapezoidal Fuzzy Number (TrFN). This research develops multivariate fuzzy T^2 Hotelling control chart with α_cut using TrFN and evaluation performance using the ARL approach and its application to the building materials industry at UD Tiga Beton as a producer of pressed bricks. Making this control chart begins with the formation of membership function matrix from the representation of the trapezoidal curve to the calculation of statistical values and plotting. The evaluation performance results of this control chart using TrFN and TFN are sensitive to a small mean shift which is indicated by a decrease in the ARL value. In addition, the use of TrFN shows that the greater the value of α_cut, which is equal to 0,9, the better the performance in controlling quality in small mean shifts, while the use of TFN shows the same performance in controlling quality in small changes with different α_cutvalues. In practice, multivariate fuzzy T^2 Hotelling control chart with α_cut of 0.9 using TFN is more sensitive in detecting out of control observations of pressed brick production at UD Tiga Beton although there is only a slight difference using the symmetric TrFN.
Item Type: | Thesis (Masters) |
---|---|
Uncontrolled Keywords: | Diagram kontrol multivariat, Fuzzy T^2 Hotelling, α_cut, TrFN, TFN, ARL, industri bahan bangunan Multivariate control charts, fuzzy T^2 Hotelling, α_cut, TrFN, TFN, ARL, building materials industry. |
Subjects: | H Social Sciences > HA Statistics > HA29 Theory and method of social science statistics H Social Sciences > HD Industries. Land use. Labor > HD31 Management--Evaluation H Social Sciences > HD Industries. Land use. Labor > HD56.25 Industrial efficiency--Measurement. Industrial productivity--Measurement. |
Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49101-(S2) Master Thesis |
Depositing User: | Nur Rezky Safitriani |
Date Deposited: | 13 Feb 2023 01:27 |
Last Modified: | 13 Feb 2023 01:27 |
URI: | http://repository.its.ac.id/id/eprint/97111 |
Actions (login required)
View Item |