当前位置: X-MOL 学术ACM Trans. Intell. Syst. Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems
ACM Transactions on Intelligent Systems and Technology ( IF 7.2 ) Pub Date : 2021-03-09 , DOI: 10.1145/3445033
Zijian Li 1 , Ruichu Cai 1 , Hong Wei Ng 2 , Marianne Winslett 3 , Tom Z. J. Fu 4 , Boyan Xu 1 , Xiaoyan Yang 5 , Zhenjie Zhang 6
Affiliation  

Data-driven models are becoming essential parts in modern mechanical systems, commonly used to capture the behavior of various equipment and varying environmental characteristics. Despite the advantages of these data-driven models on excellent adaptivity to high dynamics and aging equipment, they are usually hungry for massive labels, mostly contributed by human engineers at a high cost. Fortunately, domain adaptation enhances the model generalization by utilizing the labeled source data and the unlabeled target data. However, the mainstream domain adaptation methods cannot achieve ideal performance on time series data, since they assume that the conditional distributions are equal. This assumption works well in the static data but is inapplicable for the time series data. Even the first-order Markov dependence assumption requires the dependence between any two consecutive time steps. In this article, we assume that the causal mechanism is invariant and present our Causal Mechanism Transfer Network (CMTN) for time series domain adaptation. By capturing causal mechanisms of time series data, CMTN allows the data-driven models to exploit existing data and labels from similar systems, such that the resulting model on a new system is highly reliable even with limited data. We report our empirical results and lessons learned from two real-world case studies, on chiller plant energy optimization and boiler fault detection, which outperform the existing state-of-the-art method.

中文翻译:

机械系统时间序列域自适应的因果机制传递网络

数据驱动模型正在成为现代机械系统的重要组成部分,通常用于捕捉各种设备的行为和不同的环境特征。尽管这些数据驱动模型在对高动态和老化设备的出色适应性方面具有优势,但它们通常渴望大量标签,主要由人类工程师以高成本贡献。幸运的是,域适应通过利用标记的源数据和未标记的目标数据增强了模型的泛化能力。然而,主流的域适应方法在时间序列数据上无法达到理想的性能,因为它们假设条件分布是相等的。这种假设在静态数据中效果很好,但不适用于时间序列数据。即使是一阶马尔可夫依赖假设也需要任何两个连续时间步之间的依赖。在本文中,我们假设因果机制是不变的,并提出我们的因果机制传输网络(CMTN)用于时间序列域适应。通过捕获时间序列数据的因果机制,CMTN 允许数据驱动模型利用来自类似系统的现有数据和标签,这样即使在数据有限的情况下,新系统上的结果模型也具有很高的可靠性。我们报告了我们从两个真实案例研究中获得的经验结果和经验教训,即冷水机组能源优化和锅炉故障检测,它们的性能优于现有的最先进方法。我们假设因果机制是不变的,并提出我们的因果机制传输网络(CMTN)用于时间序列域适应。通过捕获时间序列数据的因果机制,CMTN 允许数据驱动模型利用来自类似系统的现有数据和标签,这样即使在数据有限的情况下,新系统上的结果模型也具有很高的可靠性。我们报告了我们从两个实际案例研究中获得的经验结果和经验教训,即冷水机组能源优化和锅炉故障检测,它们的性能优于现有的最先进方法。我们假设因果机制是不变的,并提出我们的因果机制传输网络(CMTN)用于时间序列域适应。通过捕获时间序列数据的因果机制,CMTN 允许数据驱动模型利用来自类似系统的现有数据和标签,这样即使在数据有限的情况下,新系统上的结果模型也具有很高的可靠性。我们报告了我们从两个实际案例研究中获得的经验结果和经验教训,即冷水机组能源优化和锅炉故障检测,它们的性能优于现有的最先进方法。这样即使数据有限,在新系统上生成的模型也非常可靠。我们报告了我们从两个实际案例研究中获得的经验结果和经验教训,即冷水机组能源优化和锅炉故障检测,它们的性能优于现有的最先进方法。这样即使数据有限,在新系统上生成的模型也非常可靠。我们报告了我们从两个实际案例研究中获得的经验结果和经验教训,即冷水机组能源优化和锅炉故障检测,它们的性能优于现有的最先进方法。
更新日期:2021-03-09
down
wechat
bug