Optimizing Powertrain Disassembly Efficiency via Machine Learning-Based Lean Six Sigma at PT. TU Surabaya Branch

Aug 5, 2026

Operational efficiency is vital in mining and construction, since equipment availability directly shapes productivity. This study evaluates reconditioning effectiveness for Powertrain components at PT. TU Surabaya, treating Disassembly as the main bottleneck in the maintenance cycle. Lean Six Sigma is implemented through DMAIC to identify, measure, analyze, and control service-duration drivers. Decision Tree Regression in KNIME predicts optimal disassembly time from historical data. After implementation, average process duration drops from 26.37 to 15.33 days and PCE rises from 46.49% to 53.20%, confirming a data-driven strategy that combines Lean Six Sigma and predictive analytics.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Introduction

Mining and construction demand for heavy equipment

Role of PT. TU and reconditioning services

Problem statement: prolonged Powertrain reconditioning at PT. TU Surabaya

Research approach: analysis of historical reconditioning jobs

Identified gap: turnaround time exceeds agreed targets

Optimizing Powertrain Disassembly Efficiency via Machine Learning-Based Lean Six Sigma at PT.TU Surabaya Branch Ditto Nadendra 1 , Wiwik Handayani2* 1, 2 Universitas Pembangunan Nasional Veteran, Jawa Timur, Indonesia Abstract Operational efficiency is vital in mining and construction, were equipment availability drives productivity. This study assesses reconditioning effectiveness for Powertrain components at PT. TU Surabaya, focusing on the Disassembly stage the primary bottleneck in the maintenance cycle. Lean Six Sigma is applied using the DMAIC (Define, Measure, Analyze, Improve, Control) framework to identify, measure, and regulate service duration factors. Machine Learning, via Decision Tree Regression in KNIME, analyzes historical data to predict optimal Disassembly timeframes. Efficiency improvement is implemented using the 5S method, while a Decision Matrix prioritizes solutions to enhance overall system performance. Results from initial implementation show a reduction in average process duration from 26.37 days to 15.33 days. Predictive analysis also reflects an increase in Process Cycle Efficiency (PCE) from 46.49% to 53.20% . These findings affirm the effectiveness of a structured, data-driven operational strategy that combines Lean Six Sigma and predictive analytics to resolve service bottlenecks and improve industrial process outcomes. Keywords: Decision Tree Regression, DMAIC, Lean Six Sigma, Operational Efficiency, Process Cycle Efficiency Article History: Received: July 13 , 2025; Accepted: September 1 , 2025; Published: September 26, 2025 *Correspondence author: [wiwik.em@upnjatim.ac.id](wiwik.em@upnjatim.ac.id) DOI: [https://doi.org/10.30871/jaba.10209](https://doi.org/10.30871/jaba.10209) JEL Code: L72, M11, D24 INTRODUCTION Indonesia abundant natural resources have positioned the mining sector as one of the key pillars of its national economy. According to data from (Badan Pusat Statistik (BPS), 2024.), mining and quarrying contributed Rp2,198,018 .10 to the national GDP in 2023. In parallel, Indonesia’s infrastructure expansion, propelled by National Strategic Projects (PSN), has significantly stimulated the construction sector, contributing Rp2,072,384 .80 to GDP and reinforcing the structural underpinnings of national economic development. Table 1. GDP on the basis of prices in business sector | Description | Amount | | --- | --- | | Manufacturing Industry | Rp3,900,061.70 | | Large and Retail | Rp2,702,445.60 | | Agriculture, Forestry and Fisheries | Rp2,617,670.00 | | Mining and quarrying | Rp2,198,018.10 | | Construction | Rp2,072,384.80 | Source: (Badan Pusat Statistik (BPS), 2024 .) As both mining and construction activities intensify, the demand for high-performance heavy equipment such as excavators, dump trucks, and bulldozers continues to rise. These machines operate in harsh environments and play a vital role in ensuring operational continuity. Their efficiency is not only determined by acquisition cost and lifespan but also by the speed and reliability of maintenance services. Timely reconditioning and reduced downtime are essential to minimize operational disruptions and cost overruns (Saputra et al. , 2023) . Given the strategic importance of reconditioning in sustaining heavy equipment performance, attention turns to key industry players that provide such services in Indonesia. In this context, PT. TU, the official distributor of Caterpillar equipment since 1971, plays a pivotal role in supporting industrial operations through its after-sales services. Among these, the System Component Reconditioning Service is particularly crucial for maintaining equipment reliability. One of PT.TU’s key branches located in Surabaya serves the East Java region, including major clients in the mining sector. However, PT.TU Surabaya has recently faced challenges in delivering timely reconditioning services, particularly for MMG a prominent mining company operating i

FAQs

What is the main bottleneck addressed in the study at PT. TU Surabaya?

The study identifies the Disassembly stage in the Powertrain reconditioning workflow as the primary bottleneck driving prolonged service duration.

How is Lean Six Sigma applied in the research?

Lean Six Sigma is executed using the DMAIC framework—Define, Measure, Analyze, Improve, and Control—to identify and manage service-duration factors.

Which machine learning method is used to predict optimal disassembly timeframes?

Decision Tree Regression in KNIME is used to analyze historical data and predict optimal disassembly timeframes.

Aug 5, 2026

Upload by Seraphina