一种用于冷水机组的数据驱动模型建模方法及系统

• Format: Patent
• Language: Chinese
• Published: 24.09.2024
• Subjects: AIR-CONDITIONING, AIR-HUMIDIFICATION, VENTILATION, USE OF AIRCURRENTS FOR SCREENING; BLASTING; CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HEATING; LIGHTING; MECHANICAL ENGINEERING; PHYSICS; RANGES; VENTILATING; WEAPONS

本发明公开了一种用于冷水机组的数据驱动模型建模方法及系统，本发明方法包括获取冷水机组的运行指标的数据，通过聚类过滤和增强来构建训练样本数据库；根据基于冷水机组运行情况确定的运行指标阈值，判断训练样本数据库是否满足数据驱动模型的建模需求，若满足数据驱动模型的建模需求，则采用训练样本数据库训练冷水机组的数据驱动模型以用于预测冷水机组的功率。本发明利用"冷机建模过程的规则"+"聚类"+"增强"多种方法的结合，能够增强样本最小代价实现数据驱动模型建模的数据准备和训练过程，实现小样本下的自动模型创建，快速实现数据驱动模型参与能源系统优化，增加人工智能在能源系统优化中落地的速度。 The invention discloses a data-driven model modeling method and system for a water chilling unit, and the method comprises the steps: obtaining the data of an operation index of the water chilling unit, and constructing a training sample database through clustering filtering and enhancement; according to an operation index threshold value determined based on the operation condition of the water chilling unit, whether the training sample database meets the modeling requirement of the data driving model or not is judged, and if the modeling requirement of the data driving model is met, the training sample database is adopted to train the data driving model of the water chilling unit so as to predict the power of the water chilli