Mestro: Jurnal Teknik Mesin dan Elektro

Acoustic Pattern Classification in Female Voice Using K-Nearest Neighbor with MFCC Feature Extraction

2026-06-28T02:27:46+00:00

This study investigates the classification of acoustic patterns in female voice signals using the K-Nearest Neighbors (KNN) algorithm and Mel-Frequency Cepstral Coefficients (MFCCs). Acoustic features derived from speech signals contain important spectral information that can be utilized to distinguish variations in voice characteristics. However, variability in speech signals and overlapping feature distributions present challenges for accurate classification. To address this issue, this study employs a structured approach comprising data preparation, MFCC feature extraction, and KNN classification. Each speech sample is represented as a 58-dimensional MFCC feature vector, and the dataset is split into testing and training subsets using a 20:80 ratio. The KNN model is trained using Euclidean distance and evaluated on precision, accuracy, recall, and F1-score. The results show that the proposed approach reaches an accuracy of 87.75%, indicating that MFCC features effectively capture acoustic characteristics in female voice signals. The confusion matrix analysis reveals that categories with distinct acoustic patterns, such as surprise and calm, achieve higher classification performance, whereas overlapping categories, such as happy and disgust, lead to increased misclassification. These findings demonstrate that KNN can serve as a reliable baseline method for acoustic pattern classification. However, further improvements can be achieved through enhanced feature representation and more advanced classification models.

Piping Stress Analysis of XYZ Platform Using CAESAR II: Compliance Verification with ASME B31.3

2026-06-28T03:23:24+00:00

This paper presents the piping stress analysis of the XYZPlatform as part of the EPCI Contract for Platform Reactivation of the XYZ Project, operated by PT. XYZ. The analysis was conducted using CAESAR II Version 2019 (11.0) for piping system Model 03, covering the pipeline from Pig Receiver (R-002) to Upstream HIPPS (Z-010). The objective was to verify compliance with ASME B31.3 (2020) Process Piping code under various load cases including hydrotest, sustained, operating, occasional, and expansion conditions. Line properties analyzed involve 8-inch and 10-inch carbon steel pipes (A106 Grade B and API 5L X52) with design pressure up to 1,550 psi and design temperature of 200°F. Results demonstrate that all maximum stresses are within allowable limits, with sustained stress ratio reaching 60.8%, occasional stress ratio at 61.2%, and thermal expansion ratio at 23.0%. Maximum displacement in the operating condition is 9.013 mm in the X-axis direction, well within the 100 mm threshold. Flange leakage verification using the Pressure Equivalent Method yields a maximum ratio of 77.72%, confirming integrity. The minimum natural frequency of the piping system is 4.585 Hz, exceeding the required 4 Hz minimum. All equipment nozzle loads at the Pig Receiver are within allowable limits per CPY-SPE-0009. The study confirms that the proposed piping configuration for XYZPlatform is structurally sound and compliant with applicable codes and project specifications.

Keywords: ASME B31.3; CAESAR II; XYZPlatform; XYZ Platform; Offshore Piping; Piping Stress Analysis

The Pengaruh Variasi Sudut Kemiringan Pisau terhadap Kapasitas Produksi dan Efisiensi Pemotongan Mesin Pencacah Rumput

2026-06-30T07:33:40+00:00

Forage is the main component in ruminant farming, but manually chopping grass is considered inefficient
in terms of time and effort. This study aims to design and build a grass chopper machine with blade angle
variations of 15°, 30°, and 60°, as well as to find out the effect of each angle on production capacity, the
quality of the chopped grass, and cutting efficiency. The machine is designed using a Honda GX160
gasoline engine with 5.5 hp, an 8:1 ratio pulley transmission system, a frame made of angle iron, and HSS
steel blades, with machine dimensions of 80 cm long, 45 cm wide, and 101.11 cm high. Testing was carried
out by inserting 3 kg of grass material for each blade angle variation. The test results showed that a 60°
blade angle couldn’t be used because it collided with the machine body. A 15° blade angle gave a
production capacity of 72 kg/hour with a cutting efficiency of 63% and uneven chopping quality.
Meanwhile, a 30° blade angle provided the best performance, with the highest production capacity of 90
kg/hour, cutting efficiency reaching 66%, and even chopped quality. Based on these results, it was
concluded that a 30° blade tilt is the most optimal angle to use on a grass chopper machine for producing
good-quality chops more efficiently.

Energy Balance, Capacity Sizing Verification, and Dioxin Risk Screening of a Titanium Structured Waste-to-Energy Incinerator: A Techno Thermal Case Study of PLTSa 10 MW Cirebon

2026-08-26T23:24:56+00:00

As Indonesia accelerates its Waste-to-Energy (WtE) program through the Pembangkit Listrik Tenaga Sampah (PLTSa) initiative, independent technical verification of proposed projects is critical to avoid costly design miscalculations. This study presents a techno-thermal simulation and independent verification of a proposed titanium-structured incinerator for the 10 MW, 600 ton/day facility under feasibility study in Cirebon, covering (i) process temperature profiling and dioxin (PCDD/F) formation-risk zoning, (ii) a first-order energy balance from feedstock lower heating value (LHV) to net electrical output, and (iii) post-air-pollution-control (APC) emission compliance. The verification reveals three critical discrepancies. First, the assumed feedstock LHV of 3,363 kcal/kg is 1.5–2.6 times higher than the 1,290–2,270 kcal/kg range typically reported for raw, high-moisture Indonesian municipal solid waste. Second, the combined conversion efficiency of 18% is markedly lower than the 28–35% efficiency reported for modern WtE plants; these two assumptions act in partly offsetting directions, meaning their net effect on the reported 76% capacity mismatch cannot be resolved without plant-specific data. Third, a specific internal inconsistency was identified: the model's net-power formula is not capped at nameplate capacity, producing a physically impossible capacity factor of 135%. Benchmarking against five comparable Indonesian PLTSa projects (Surakarta, Surabaya–Benowo, Semarang, Palembang, and Cirebon itself) shows specific electricity yields of 220–527 kWh per ton of waste, within which the Cirebon plant's planned 10 MW/600 tpd (400 kWh/ton) falls squarely, suggesting the nameplate rating itself is a defensible design choice rather than an undersizing error. Dioxin-risk zoning, using a 400–650 °C de novo formation window, identifies the superheater, economizer, and air-heater zones as high risk; however, the 325 °C APC-inlet zone sits within the 250–350 °C peak de novo window reported in the literature, indicating the model's 400 °C lower bound may understate risk. Emission compliance analysis, cross-checked against the actual Indonesian thermal-waste-treatment standard (Permen LHK No. P.70/2016), shows that the model's sole reported "failure" (particulate matter) does not constitute regulatory non-compliance, as the modeled concentration of 25 mg/Nm³ is well within the national limit of 120 mg/Nm³. Consequently, the reported 76% capacity mismatch, while indicative, is not a validated design flaw. This finding underscores the necessity of grounding screening-level simulations in plant-specific data and verified local regulations to inform sound engineering, policy, and investment decisions in Indonesia's emerging WtE sector.

Penentuan Ukuran Optimal Turbin Angin dan Sistem Penyimpanan Energi Baterai untuk Keandalan Jaringan Listrik dan Pengurangan Emisi Karbon: Studi Kasus Pulau Karimunjawa, Indonesia

2026-08-29T02:25:29+00:00

Integrasi sumber energi terbarukan, seperti turbin angin, dengan sistem penyimpanan energi baterai (BESS) sangat penting untuk meningkatkan keandalan jaringan mikro pulau dan mengurangi emisi karbon dari pembangkit listrik berbasis diesel. Penelitian ini menyajikan analisis tekno-ekonomi dan lingkungan menggunakan skrip simulasi berbasis Python untuk menentukan ukuran optimal turbin angin Goldwind GW50-750 dan BESS guna memenuhi profil beban Pulau Karimunjawa, Indonesia, dengan Probabilitas Kehilangan Beban (LSLP) di bawah 5%. Analisis ini menggabungkan data angin selama 12 tahun (2004–2015), profil beban per jam, dan perhitungan emisi karbon berdasarkan penggantian pembangkit diesel dari PLTD Legon Bajak (2x2,2 MW). Hasil menunjukkan konfigurasi optimal berupa 2 turbin angin (kapasitas total 1,50 MW) dan BESS 100 MWh, yang mencapai LSLP 0,00% dan pengurangan karbon tahunan sebesar 6.964 ton CO₂-eq. Simulasi menunjukkan bahwa semua konfigurasi yang diuji memenuhi target keandalan berkat kapasitas cadangan diesel, dengan pengurangan karbon meningkat seiring penambahan kapasitas BESS hingga mencapai titik jenuh. Penghematan bahan bakar tahunan mencapai 2.598.701 liter, dengan manfaat ekonomi termasuk penghematan biaya bahan bakar sebesar Rp 31.184.413.441. Analisis sensitivitas mengonfirmasi ketahanan sistem terhadap variasi kecepatan angin. Pendekatan ini menyediakan kerangka kerja yang dapat diskalakan untuk perencanaan energi berkelanjutan di pulau-pulau terpencil.