Optimizing Energy Efficiency in Wood Processing Plants through Data Analysis: A Case Study on Value-Added Wood Products Manufacturing

Year 2024, Volume: 7 Issue: 1, 48 - 63, 21.11.2024

Melike Nur İnce , Çağatay Taşdemir

Abstract

Energy consumption in value-added wood products manufacturing facilities has significant environmental and economic impacts. High energy usage increases costs and expands the carbon footprint, making it challenging to achieve sustainability goals. Inefficient energy management in wood processing plants elevates operational costs and exacerbates the environmental burden. Therefore, optimizing energy efficiency through data analysis techniques is critically important. This study analyzes energy consumption data to identify inefficiencies and propose effective optimization strategies. Historical data encompassing operational parameters, energy consumption, environmental conditions, and production output from five high-capacity wood processing machines in the wood products industry were collected daily over the past three years. The dataset includes ten categories: Date, Machine ID, Runtime Hours, Load Percentage, Electricity Usage, Gas Usage, Temperature, Humidity, Production Output, and Energy Efficiency. Initially, the data were loaded into a pandas Data Frame, converted to date and time format, and checked for missing and outlier values, followed by standardization of numerical features. Descriptive statistics were calculated for each feature, and data consistency was verified. The distributions of critical features were visualized with histograms, and the relationships between numerical features were illustrated using a correlation matrix heatmap. Trends and seasonal patterns in energy consumption and production output were analyzed by resampling the data monthly. Principal Component Analysis (PCA) was applied to reduce the dimensionality of the dataset while retaining significant information, and three clusters were formed using the K-Means algorithm. The clusters were visualized in the PCA-reduced feature space, and their characteristics were analyzed to prioritize machines for energy efficiency improvements. Cluster 2, characterized by an average energy usage of 209.79 kWh, an average gas usage of 107.90 m³, an average production output of 1595.03 units, an average energy efficiency of 5.26 units/kWh, and an average load percentage of 75.35%, demonstrated low energy consumption and high production output, indicating highly efficient operations. Therefore, it is recommended that the best practices from this cluster be standardized and implemented across other clusters. Additionally, investing in technological advancements to enhance energy efficiency and conducting continuous improvement efforts to maintain and improve efficiency are suggested.

Keywords

Energy Efficiency, K-Means Clustering, Principal Component Analysis (PCA), Wood Products Industry

References

• Statista. “Estimated value of the furniture market worldwide from 2022 to 2030”. https://www.statista.com/statistics/977793/furniture-market-value-worldwide/ (10.08.2024).
• Fortune Business Insights. “Furniture Market Size, Industry Share & COVID-19 Impact Analysis, By Raw Material (Wood, Metal, Plastic, and Others), Category (Indoor and Outdoor), End-User (Residential, Office, Hotel, and Others), and Regional Forecast, 2023-2030”. https://www.fortunebusinessinsights.com/furniture-market-106357 (5.08.2024).
• Global Market Insights. “Wooden Furniture Market - By Product Type (Indoor Furniture, Outdoor Furniture), By Wood Type (Hardwood, Softwood), By Price, By Application, By Distribution Channel Forecast 2024 – 2032”. https://www.gminsights.com/industry-analysis/wooden-furniture-market (5.08.2024)..
• Imarc Transforming Ideas into Impact. “Wood Furniture Market by Wood Type (Hardwood, Softwood), Distribution Channel (Retail, Online), End User (Residential, Commercial), and Region 2024-2032”. https://www.imarcgroup.com/wood-furniture-market (07.08.2024).
• Sihn W, Sobottka T, Heinzl B, Kamhuber F. “Interdisciplinary Multi-Criteria Optimization Using Hybrid Simulation to Pursue Energy Efficiency Through Production Planning”. CIRP Annals, 67(1), 447-450, 2018.
• Wen X, Cao H, Hon B, Chen E, Li H. “Energy Value Mapping: A Novel Lean Method to İntegrate Energy Efficiency into Production Management”. Energy, 217, 119353, 2021.
• Sobottka T, Kamhuber F, Sihn W. “Increasing Energy Efficiency in Production Environments Through an Optimized, Hybrid Simulation-Based Planning of Production and its Periphery”. The 24th CIRP Conference on Life Cycle Engineering, Kamakura, Japan, 8-10 March 2017.
• Bonfa F, Benedetti M, Ubertini S, Introna V, Satolamazza a. “New Efficiency Opportunities Arising from Intelligent Real Time Control Tools Applications: The Case of Compressed Air Systems’ Energy Efficiency in Production and Use”. 10th International Conference on Applied Energy (ICAE2018), Hong Kong, China, 22-25 August 2018.
• Benedetti M, Bertini I, Bonfà F, Ferrari S, Introna V, Santino D, Ubertini S. “Assessing and Improving Compressed Air Systems’ Energy Efficiency in Production and Use: Findings from an Explorative Study in Large and Energy-Intensive Industrial Firms”. The 8th International Conference on Applied Energy (ICAE2016), Beijing, China, 81 October 2016.
• Emre İ.E, Selcukcan Erol C. “Statistics or Data Mining for Data Analysis”. Journal of Information Technologies, 10(2), 161-167, 2017.
• Bennert T, Hanson D, Maher A. “Influence of pavement surface type on tire/pavement generated noise”. Journal of Testing & Evaluation, 33(2), 94-100, 2005.
• Wold S, Esbensen K, Geladi P. “Principal Component Analysis”. Chemometrics and Intelligent Laboratory Systems, 2(1-3), 37-52, 1987.
• Ghiasi S, Srivastava A, Yang X, Sarrafzadeh M. “Optimal Energy Aware Clustering in Sensor Networks”. Sensors, 2, 258-269, 2002.
• Abdi H, Williams L.J. “Principal Component Analysis.” WIREs Computational Statistics, 2(4), 433-459, 2010.
• Bro R, Smilde A.K. “Principal Component Analysis”. Analytical Methods, 6(9), 2812-2831, 2014.
• Zhou W, Xu K, Yang Y, Lu J. “Driving Cycle Development for Electric Vehicle Application Using Principal Component Analysis and K-Means Cluster: With The Case of Shenyang, China”. 8th International Conference on Applied Energy (ICAE2016), Beijing, China, 8-11 October 2016.
• Chen Z, Xiong R. “Driving Cycle Development for Electric Vehicle Application Using Principal Component Analysis and K-Means Cluster: With The Case of Shenyang, China”. 9th International Conference on Applied Energy (ICAE2017), Cardiff, UK, 21-24 August 2017.
• Pořízka P, Klus J, Képeš E, Prochazka D, Hahn D.W. “On The Utilization of Principal Component Analysis in Laser-Induced Breakdown Spectroscopy Data Analysis, A Review”. Spectrochimica Acta Part B, 148, 65-82, 2018.
• Cebeci Z. “fcvalid: An R Package for Internal Validation of Probabilistic and Possibilistic Clustering”. Sakarya Unıversıty Journal of Computer and Informatıon Scıences, 3(1), 11-27, 2020.
• Clayman C.L, Srinivasan S.M, Sangwan R.S. “K-means Clustering and Principal Components Analysis of Microarray Data of L1000 Landmark Genes”. Procedia Computer Science, 168, 97-104, 2020.
• Jannson N.F, Allen R.L, Skogsmo G, Tavakoli S. “Principal Component Analysis and K-Means Clustering as Tools During Exploration for Zn Skarn Deposits and Industrial Carbonates, Sala Area, Sweden”. Journal of Geochemical Exploration, 233, 106909,2022.
• Ilu S.Y, Rajesh P, Mohammed H. “Prediction of COVID-19 Using Long Short-Term Memory By Integrating Principal Component Analysis And Clustering Techniques”. Informatics in Medicine Unlocked, 31, 100990, 2022.
• Liao J, Lin J, Wu G. “Two-Layer Optimization Configuration Method for Distributed Photovoltaic and Energy Storage Systems Based on IDEC-K Clustering”. Energy Reports, 11, 5172-5188, 2024.
• Eid M.H, Eissa M, Mohamed E.A, Ramadan H.S, Czuppon G, Kovacs A, Szűcs P. “Application of Stable Isotopes, Mixing Models, and K-Means Cluster Analysis to Detect Recharge and Salinity Origins In Siwa Oasis, Egypt”. Groundwater for Sustainable Development, 25, 101124, 2024.
• Dugan E.L, Barbuto A.E, Masterson C.M, Shilt J, “Multivariate Functional Principal Component Analysis and K-Means Clustering to Identify Kinematic Foot Types During Gait in Children with Cerebral Palsy”. Gait & Posture, 113, 40-45, 2024.
• Gürcan E. K., Soysal M. İ., Genç S. “The Determination of Relationships Between Live Weight with Various Body Measurement in Japanese Quail Using Principal Component Analysis”. Journal of Poultry Research. 9(1), 27-33, 2010.
• Durgun B., Uygur V., Durgun B., Sukuşu E. “Assessment of Relations Between Micro Element Availability and Soil Properties in Isparta-Atabey Plain Using Principal Component Analysis”. Anadolu Journal of Agricultural Sciences. 32(2), 258-268, 2017.
• Çolak B., Durdağ Z., Erdoğmuş P. “Automatic Clustering with K-Means”. El-Cezerî Journal of Science and Engineering. 3(2), 315-323, 2016.
• Arya N. (2023, November 10). K-Means Clustering for Unsupervised Machine Learning. EJable. https://www.ejable.com/tech-corner/ai-machine-learning-and-deep-learning/k-means-clustering.