使用不同的机器学习方法预测生物营养除去 (BNR) 过程的废水参数:一个案例研究.
Neslihan Manav-Demir1, Huseyin Baran Gelgor1, Ersoy Oz2
1Yildiz Technical University, Environmental Engineering Department, Esenler, Istanbul, 34220, Turkey.
Journal of environmental management
|December 30, 2023
概括
本研究使用机器学习 (ML) 来预测废水处理厂 (WWTP) 废水的排放参数. 选择性ML算法应用提高了生物营养去除 (BNR) 过程的预测准确性,减少了监测需求.
科学领域:
- 环境工程 环境工程
- 水处理技术水处理技术
- 机器学习应用 机器学习应用
背景情况:
- 废水处理厂 (WWTP) 需要精确的操作控制,以有效地去除营养物质.
- 预测废水参数对于监测环境性能和监管合规性至关重要.
- 机器学习 (ML) 提供了提高WWTP操作中的预测能力的潜力.
研究的目的:
- 提出和评估一种针对性的ML算法组合,用于控制WWTP操作.
- 预测生物营养物去除 (BNR) 过程中的关键废水参数.
- 为了比较六个ML算法的排放物参数预测性能.
主要方法:
- 收集了Plajyolu WWTP在土耳其Kocaeli的两年运营数据.
- 应用了六个ML算法:支持向量回归机 (SVRM),随机森林 (RF),极端梯度提升 (XGBoost),轻GBM和混合回归.
- 使用包括平均绝对百分比误差 (MAPE) 在内的指标评估算法性能.
主要成果:
- 带有线性内核的SVRM显示了化学氧气需求 (COD) 和BOD5 (MAPE ~9%和0.9%) 的高精度.
- 射频和XGBoost对于总 (TN) 和总 (TP) 的预测是最佳的 (MAPE~34%和27%).
- 射频,SVRM (线性和RBF内核) 和混合回归在所有参数中普遍超过其他算法.
结论:
- 选择性应用ML算法可以有效地预测不同的WWTP废水参数.
- 这种方法可以提高WWTP环境绩效监测的效率.
- 更广泛地实施基于机器学习的预测可以减少对主动监控的资源需求.
相关概念视频
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
56
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
56
01:30Typical Model Studies
359
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
359