基于混合慢特征分析的集成热泵系统IIoT-Enabled健康监测
IIoT-Enabled Health Monitoring for Integrated Heat Pump System Using Mixture Slow Feature Analysis
摘要：
传感技术的持续发展和通信技术的进步已经彻底改变了各种电气设备的性能和健康管理，使其朝着数据驱动的方向发展。这场革命为热泵（HP）系统的健康监测问题提供了一个有前途的解决方案，热泵系统是现代建筑中广泛部署的重要设备，用于供暖，以及时评估其运行状态，避免意外停机。许多HP实际上是在多年前制造和安装的，由于当时的技术限制和成本控制，导致可用的传感器较少。它提出了一个难题，以负担得起的成本保护惠普。我们提出了一种混合方案，通过集成工业物联网（IIoT）和智能健康监测算法来应对这一挑战。首先，构建一个IIoT网络来感测和存储测量结果。具体地，温度传感器被适当地选择并部署在水箱的入口和出口处以测量水温。其次，利用温度信息，提出了一种无监督学习算法混合慢特征分析（MSFA），以及时评估集成HP的健康状况。由于热水需求的变化，不同的HP频繁的操作开关的特点，观察到不同的加热速度的各种加热模式。慢度是衡量稳态分布变化速度的一种动力学指标，MSFA在加热模式划分和健康评价中均适当考虑了慢度的影响。最后，所提出的方法的有效性进行了验证，通过一个真正的集成HP与五个连接的HP安装十年前。实验结果表明，MSFA是能够准确地识别系统的健康状态，特别是在初始阶段的故障相比，其竞争算法。
英文摘要：
The sustaining evolution of sensing and advancement in communications technologies have revolutionized prognostics and health management for various electrical equipment towards data-driven ways. This revolution delivers a promising solution for the health monitoring problem of heat pump (HP) system, a vital device widely deployed in modern buildings for heating use, to timely evaluate its operation status to avoid unexpected downtime. Many HPs were practically manufactured and installed many years ago, resulting in fewer sensors available due to technology limitations and cost control at that time. It raises a dilemma to safeguard HPs at an affordable cost. We propose a hybrid scheme by integrating industrial Internet-of-Things (IIoT) and intelligent health monitoring algorithms to handle this challenge. To start with, an IIoT network is constructed to sense and store measurements. Specifically, temperature sensors are properly chosen and deployed at the inlet and outlet of the water tank to measure water temperature. Second, with temperature information, we propose an unsupervised learning algorithm named mixture slow feature analysis (MSFA) to timely evaluate the health status of the integrated HP. Characterized by frequent operation switches of different HPs due to the variable demand for hot water, various heating patterns with different heating speeds are observed. Slowness, a kind of dynamics to measure the varying speed of steady distribution, is properly considered in MSFA for both heating pattern division and health evaluation. Finally, the efficacy of the proposed method is verified through a real integrated HP with five connected HPs installed ten years ago. The experimental results show that MSFA is capable of accurately identifying health status of the system, especially failure at a preliminary stage compared to its competing algorithms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
