Representing Small Commercial Building Faults in EnergyPlus, Part I: Model Development

Abstract

Small commercial buildings (those with less than approximately 1000 m2 of total floor area) often do not have access to cost-effective automated fault detection and diagnosis (AFDD) tools for maintaining efficient building operations. AFDD tools based on machine-learning algorithms hold promise for lowering cost barriers for AFDD in small commercial buildings; however, such algorithms require access to high-quality training data that is often difficult to obtain. To fill the gap in this research area, this study covers the development (Part I) and validation (Part II) of fault models that can be used with the building energy modeling software EnergyPlus® and OpenStudio® to generate a cost-effective training data set for developing AFDD algorithms. Part I (this paper) presents a library of fault models, including detailed descriptions of each fault model structure and their implementation with EnergyPlus. This paper also discusses a case study of training data set generation, representing an actual building.

Review on Fault Detection and Diagnosis Feature Engineering in Building Heating, Ventilation, Air Conditioning and Refrigeration Systems

“…Owing to the time-consuming and labour-intensive characteristics of human-designed fault experiments, researchers have begun to perform FE research via fault simulations -generating fault data via fault modelling and simulations can be less expensive than the alternative. Some developed simulated fault models [90][91][92][93][94] and analysed fault impacts using software such as EnergyPlus [95][96][97], BIM [94,98,99], Modelica [100][101][102], TRNSYS [103][104][105], HVACSIM+ [106] and Simulink [107]. In addition, some practical fault-operating data can be stored or processed online for FDD and FE purposes.…”

Empirical Modeling of Direct Expansion (DX) Cooling System for Multiple Research Use Cases

“…Many previous works investigated RTU faults in an automated fashion [11] or by leveraging a virtual sensor set [23] that calculates the cooling energy to compare it with an empirical model to distinguish faulty operation. In addition, a detailed HVAC model was empirically validated with experiments [24] and used to develop automated FDD tools in a BES program (e.g., EnergyPlus, OpenStudio) [25,26]. This is capable of generating fault data as training sets to develop an FDD algorithm.…”

“…The setpoint temperature of all rooms was set to 23.9 • C (75 • F). The detailed information regarding the experiments was described in a previous study [26].…”

Representing Small Commercial Building Faults in EnergyPlus, Part II: Model Validation

“…The baseline results illustrated in tables and figures in the following subsections represent Baseline 1 measurements listed in Figure 2 and Table 3. Detailed description of each fault model can be found in Part I of this article series [1].…”

“…In Part I of this study [1], we presented the primary motivation for this research: the development of accurate models for building faults for use in training automated fault detection and diagnosis (AFDD) algorithms. The availability of accurate physical models for building faults advances several key areas of fault detection and diagnosis (FDD) research, including projection of regional or national fault energy impacts [2,3], development of model-based FDD algorithms [4,5], and simulation-based assessment of FDD algorithm performance [6,7].…”