MODEL PREDIKSI ENERGI HARVESTING PADA KARPET PINTAR PIEZOELEKTRIK BERBASIS MULTILAYER PERCEPTRON (MLP) DENGAN VARIASI POLA LANGKAH MANUSIA
DOI:
https://doi.org/10.52453/technologic.v17i1.517Keywords:
Energy Harvesting, Multi-Layer Perceptron, Piezoelectric Smart CarpetAbstract
Penelitian ini mengembangkan model prediksi berbasis Multi-Layer Perceptron (MLP) untuk output energi piezoelectric smart carpet, dengan fokus pada lima variasi pola langkah manusia: lari, jalan cepat, normal, lambat, dan hentak. Berbeda dari penelitian sebelumnya yang menggunakan pola langkah seragam, penelitian ini memodelkan keberagaman gait sebagai variabel laju gerak (Rate of Motion) dinamis untuk mencerminkan perilaku pejalan kaki yang lebih realistis. Data eksperimental dikumpulkan dari 5 subjek dengan variasi berat 54–98 kg menggunakan konfigurasi rangkaian seri-paralel piezoelectric. Model MLP dirancang dengan arsitektur 3 hidden layer (64, 32, 16 neuron), learning rate 0.001, dan mekanisme early stopping, dengan input berat subjek dan laju gerak serta output tegangan, arus, dan daya. Hasil evaluasi menunjukkan R² sebesar 0.8654 (tegangan), 0.8759 (arus), dan 0.8873 (daya), dengan MAPE masing-masing 9.55%, 10.42%, dan 30.22%. Nilai MAPE daya yang lebih tinggi merupakan konsekuensi matematis dari propagasi error pada P = V × I. Analisis korelasi mengkonfirmasi laju gerak sebagai faktor dominan (r = 0.706–0.721) dibanding berat (r = 0.303–0.491). Model ini diarahkan untuk implementasi di pintu masuk Gedung Jurusan Teknik Elektro Politeknik Negeri Sriwijaya.
References
R. R. Moussa, W. S. E. Ismaeel, and M. M. Solban, “Energy generation in public buildings using piezoelectric flooring tiles; A case study of a metro station,” Sustain. Cities Soc., vol. 77, Feb. 2022, doi: 10.1016/j.scs.2021.103555.
D. G. Wakshume and M. Ł. Płaczek, “Optimizing Piezoelectric Energy Harvesting from Mechanical Vibration for Electrical Efficiency: A Comprehensive Review,” Electronics, Mar. 2024, doi: 10.3390/electronics13050987.
I. Kareem, M. A. Chowdhury, M. K. Hossain, dan M. Z. Islam, “A Review of Piezoelectric Energy Harvesting: Materials, Design, and Readout Circuits,” Actuators, vol. 12, no. 12, p. 457, Dec. 2023, doi: 10.3390/act12120457.
H. Liu, J. Zhong, C. Lee, S.-W. Lee, dan L. Lin, “Piezoelectric Energy Harvesting Technology: From Materials, Structures, to Applications,” Small Structures, vol. 3, no. 4, p. 2100128, 2022, doi: 10.1002/sstr.202100128.
M. A. Rahman, M. T. Uddin, dan M. A. Hossain, “Piezoelectric Energy Harvesting: A Systematic Review of Reviews,” Actuators, vol. 10, no. 12, p. 312, Nov. 2021, doi: 10.3390/act10120312.
N. Sezer dan M. Koç, “A comprehensive review on the state-of-the-art of piezoelectric energy harvesting,” Nano Energy, vol. 80, p. 105567, Feb. 2021, doi: 10.1016/j.nanoen.2020.105567.
Y. Meng, G. Chen, and M. Huang, “Piezoelectric Materials: Properties, Advancements, and Design Strategies for High-Temperature Applications,” Nanomaterials, Apr. 2022, doi: 10.3390/nano12071171.
Y. Bai, “RELU-Function and Derived Function Review,” SHS Web of Conferences, vol. 144, p. 02006, 2022, doi: 10.1051/shsconf/202214402006.
S. R. Dubey, S. K. Singh, dan B. B. Chaudhuri, “Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark,” Neurocomputing, vol. 503, pp. 92–108, Sep. 2022, doi: 10.1016/j.neucom.2022.06.111.
S. Trolier-McKinstry, L. Q. Chen, D. G. Schlom, dan S. K. Streiffer, “Ferroelectricity in Ultrathin Perovskite Films,” Annual Review of Materials Research, vol. 51, pp. 353–380, 2021, doi: 10.1146/annurev-matsci-070920-012421.
C. Moreira, A. Fonseca, J. Vaz, A. Carvalho, dan J. Vinhas, “A biomechanics dataset of healthy human walking at various speeds, step lengths and step widths,” Scientific Data, vol. 9, p. 708, Nov. 2022, doi: 10.1038/s41597-022-01817-1.
M. M. Ahsan et al., “Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance,” Technologies, vol. 9, no. 3, p. 52, Jul. 2021, doi: 10.3390/technologies9030052.
W. Kim, “Comparison of Statistical Metrics for Machine Learning Performance,” Journal of Sensors, vol. 2022, p. 6507524, 2022, doi: 10.1155/2022/6507524.
A. Man, C. Chaichana, S. Wicharuck, and D. Rinchumphu, “Predicting sunlight availability for vertical shelves using simulation,” in IOP Conference Series: Earth and Environmental Science, 2022, doi: 10.1088/1755-1315/1094/1/012011.
A. de Myttenaere, B. Golden, B. Le Grand, and F. Rossi, “Mean Absolute Percentage Error for regression models,” Neurocomputing, vol. 192, pp. 38–48, Jun. 2016, doi: 10.1016/j.neucom.2015.12.114.
I. Nabillah and I. Ranggadara, “Mean Absolute Percentage Error untuk Evaluasi Hasil Prediksi Komoditas Laut,” JOINS (Journal of Information System), vol. 5, no. 2, pp. 250–255, Nov. 2020, doi: 10.33633/joins.v5i2.3900.
T. Qiu et al., “Edge Computing in Industrial Internet of Things Environment: An Overview of the Architecture and Its Issues,” IEEE Communications Surveys & Tutorials, vol. 22, no. 4, pp. 2462–2488, 2020, doi: 10.1109/COMST.2020.3007218.
C. Brambilla, M. Guardato, G. Casali, dan L. Mazzola, “Biomechanical Analysis of Human Gait When Changing Velocity and Carried Loads,” Biology, vol. 13, no. 5, p. 321, May 2024, doi: 10.3390/biology13050321.
V. Borisov et al., “Deep Neural Networks and Tabular Data: A Survey,” IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 6, pp. 7499–7519, Jun. 2024, doi: 10.1109/TNNLS.2022.3229602.
A. A. Nugraha, L. Wijanarno, A. Rosadi, dan Hadiyanto, “Pemanfaatan Energi Angin Cooling Tower Sebagai Sumber Energi Alternatif di Area Painting PT Astra Daihatsu Motor Karawang,” Technologic, vol. 15, no. 1, Jun. 2024, doi: 10.52453/t.v15i1.369.
A. E. Widyartono, Y. A. Purwoko, dan I. N. Kesawa, “Prediksi Jalur Jalan Berbasis Kalman Filter pada Sistem ADAS Menggunakan Hough Transform dengan Kamera Bersudut Pandang Terbatas,” Technologic, vol. 16, no. 1, Jun. 2025, doi: 10.52453/t.v16i1.472.
