使用机器学习技术,预测模拟和优化食品废弃物水热碳化中的化合物特性
Chinenye Adaobi Igwegbe1, Waheed A Rasaq2, Prosper Eguono Ovuoraye3
1Department of Applied Bioeconomy, Wrocław University of Environmental and Life Sciences, 37a Chełmońskiego Str., 51-630 Wrocław, Poland; Department of Chemical Engineering, Nnamdi Azikiwe University, P.M.B. 5025, Awka 420218, Nigeria.
Bioresource technology
|September 11, 2025
概括
机器学习优化了食品废弃物的碳化合物生产,每100克干废物产生48.5g. XGBoost模型准确地预测了电特性,增强了能源回收和碳保留,以实现可持续的废物转化.
科学领域:
- 可持续化学 可持续化学
- 废弃物转化为能源的技术
- 材料科学 材料科学 材料科学
背景情况:
- 水热碳化 (HTC) 将食物废物转化为有价值的碳化合物,用于能源和土壤应用.
- 优化HTC是复杂的,因为温度,时间和催化剂剂量等参数相互作用.
- 机器学习 (ML) 为预测和优化HTC流程提供了一种有前途的方法.
研究的目的:
- 应用ML技术来预测和优化食品废弃物的碳化合物产量和特性.
- 评估XGBoost,SVR和LR模型在预测HTC结果中的性能.
- 为了确定影响炭特性的关键过程参数.
主要方法:
- 分析的HTC过程参数:温度 (120-360°C),催化剂剂量 (0-2g),停留时间 (30-270分钟) 和水分含量.
- 开发并比较了三个ML模型:XGBoost (XGB),支持向量回归 (SVR) 和线性回归 (LR).
- 使用R2,MAE和RMSE指标评估模型的预测准确性,并确定参数的重要性.
主要成果:
- XGBoost实现了最高的预测准确度 (R2=0.87,MAE=0.81,RMSE=1.02),表现优于SVR和LR.
- 温度 (重要性=0.91) 和催化剂剂量 (0.61) 是影响炭产量和性能的最重要因素.
- 优化条件产生了48.5g的碳化合物/100g的干废物,能量回收率为68%.
- TiO2纳米粒子显著提高了碳保留率 (56.8%至77.6%),散装密度 (0.37至0.89g/cm3) 和加热值 (18.4至22.7MJ/kg).
结论:
- 基于机器学习的优化有效地预测和增强通过HTC从食品废物中产生碳化合物.
- XGBoost是一个适合实时HTC过程控制的模型,减少了实验工作.
- 这种方法促进了可持续的废物转化为能源,改善了资源利用和环境修复潜力.
相关概念视频
01:26Microbial Bioremediation of Hydrocarbons
Bioremediation is an environmentally sustainable process that employs living organisms—primarily microorganisms—to degrade or neutralize pollutants from contaminated environments. In oil spills and hydrocarbon pollution, bioremediation involves the use of hydrocarbon-degrading bacteria to transform toxic compounds into less harmful substances. This approach leverages natural microbial metabolic processes and is considered both cost-effective and ecologically favorable compared to physical or...
01:30Microbial Wastewater Treatment
Microbial communities in aquatic ecosystems play a key role in the natural breakdown of contaminants introduced through domestic and industrial effluents. Acting as biological catalysts, these microbes change and mineralize a wide range of organic and inorganic pollutants under different redox conditions.In oxygen-rich surface waters, aerobic heterotrophs lead organic matter breakdown, using oxygen as the terminal electron acceptor to efficiently oxidize substrates to carbon dioxide and water.
01:28Methods of Medium Optimization
Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...