数据驱动软传感器用于在线组合估计,具有自适应窗口回归和QP受约束的卡尔曼估计器
Bharati Sagi1, Thangavelu Thyagarajan2
1Dept. of Electronics and Instrumentation Engineering, VNR Vignana Jyothi Institute of Engineering and Technology, Hyderabad, 500118, India.
ISA transactions
|December 21, 2025
概括
这项研究引入了用于工业蒸的混合软传感器,提高了能源效率. 新型的自适应窗口 - 基于点位线性回归的二进制程序受约卡尔曼估计器 (AW-PLR QP-CKE) 增强了实时组合估计.
科学领域:
- 化学工程是化学工程的重要组成部分.
- 过程控制 过程控制
- 数据驱动的建模数据驱动的建模
背景情况:
- 在线成分估计对于工业蒸中的能源效率至关重要.
- 经典和数据驱动的方法与非线性,漂移和噪声作斗争.
- 现有的技术在动态条件下产生低于最佳的性能.
研究的目的:
- 开发一个强大的混合软传感器,用于准确的在线组合估计.
- 提高蒸过程中的适应性和计算效率.
- 克服传统基于模型和数据的估计器的局限性.
主要方法:
- 基于二次程序的受约束卡尔曼估计器 (QP-CKE) 与零碎线性回归 (PLR) 的集成.
- 实现PLR的自适应窗口 (AW) 扩展,使用CUSUM非线性指数调整窗口长度.
- 在试点规模的乙醇-水蒸柱上进行验证,与EKE,静态QP-CKE和SVM进行基准测试.
主要成果:
- 基于AW-PLR的QP-CKE显示了35%更低的根平均平方误差 (RMSE) 和22%更高的信号对噪声比 (SNR).
- 与基准数据相比,实现了25%更快的计算时间.
- 展现出优越的噪声弹性和流程可解释性.
结论:
- 拟议的混合软传感器提供了增强的适应性,计算效率和稳定性.
- 它适用于蒸中的实时软传感和控制框架.
- 该方法有效地处理非静止的过程行为和短暂的过程.
相关概念视频
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
1.1K
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
On...
1.1K
Estimation of the Physical Quantities
7.2K
On many occasions, physicists, other scientists, and engineers need to make estimates of a particular quantity. These are sometimes referred to as guesstimates, order-of-magnitude approximations, back-of-the-envelope calculations, or Fermi calculations. The physicist Enrico Fermi was famous for his ability to estimate various kinds of data with surprising precision. Estimating does not mean guessing a number or a formula at random. Instead, estimation means using prior experience and sound...
7.2K


