Jiri Rojicek

Fault Diagnosis of Air Handling Units

Abstract This paper presents an improved method for fault detection and diagnostics (FDD) of air handling units (AHUs). The fault detection module defines observable states of the AHU, where each state depends on current values of sensor data and control signals. The fault diagnostic module maps the observable states to the faults and then applies the cumulative sum chart (CUSUM) to define the size and development of each fault in time. The FDD method was tested on real datasets and its results were confirmed by the building technician. Finally, the method is compared with the standard APAR (AHU performance assessment rules) method developed by Schein et al.

Knowledge-Based Fault Propagation in Building Automation Systems

This paper describes a knowledge-based approach that can reason about effects of faults and causes of abnormal situations in building automation systems (BAS). Combining an ontology-based building information model (BIM), which models a BAS formally and semantically, with rules encoding expert knowledge, the fault propagation approach can automatically determine causalities in BAS and propagate faults along the causalities in both forward and backward direction. This enables an immediate assessment of potential consequences of faults respectively an analysis of the root cause(s). The fault propagation approach can enhance fault detection and diagnosis by considering BAS as a whole, being aware of the potentially far reaching consequences of faults, instead of just focusing on single pieces of equipment or zones. This provides a better understanding of BAS and improves the decision making and prioritization of the right emergency and maintenance actions.

From Symptoms to Faults: Temporal Reasoning Methods

Complex systems composed of many components can operate in an inappropriate way. Information about the system is obtained in time, gradually. The assessment of casualties in such situation has challenged many researchers. The present paper provides a new compact methodology for diagnostics of faults form measurements: Space of measurements is divided into symptoms. Each symptom is able to admit some faults as possible and exclude some as impossible. This concept is based on fuzzy logic approach and provides an efficient alternative to usual probabilistic oriented methodologies. These relations between symptoms and faults are stated in the mapping table as logical rules. The diagnosis information is gathered online and aggregated on the side of symptoms or on the side of faults. This paper provides and compares a set of different methods for transformation of measured information into truth rates for each fault.

Automatic setup of fault detection algorithms in building and home automation

The complexity and diversity of building automation systems (BAS) and the various faults that may happen in buildings make it very challenging to set up fault detection and diagnostics (FDD). This knowledge-intensive, expensive tasks urgently needs to be automated due to the limited time and budget available in this domain. A novel approach for computer-aided, automatic setup of FDD for BAS is described in this paper. Using the Web Ontology Language (OWL), the characteristics, requirements and necessary configuration of the FDD algorithms are formally specified in a machine-interpretable way. Also buildings and their BAS are described by OWL as building information model (BIM). Given these descriptions, the approach can match the specific characteristics and requirements of the FDD algorithms with the specific circumstances in the BAS in a formal evaluation process. All applicable FDD algorithms can be determined and subsequently configured to the individual characteristics of the BAS.

Ontology-based automatic setup of virtual sensors in building automation systems

Effective monitoring, fault detection and diagnostics (FDD) of building automation systems require a large number of datapoints. But the set of available sensors in a building is typically limited. Virtual sensors (VS) can be applied as cost saving alternative to real sensors. Implementing and setting up VS however can be a complex tasks that urgently needs to be automated. A novel approach for computer-aided, automatic setup of VS is presented. It is based on reusing generic, pre-implemented VS algorithms. Using OWL, the characteristics, requirements and configuration of the VS algorithms are specified in a machine-interpretable way. By that, the approach can match the specific characteristics and requirements of the VS algorithms in a formal evaluation process with the specific circumstances in the BAS, which are described in an ontology-based building information model (BIM). All applicable VS algorithms can be determined and subsequently configured to the individual characteristics of the BAS.

Black-Box Optimization for Buildings and Its Enhancement by Advanced Communication Infrastructure

The solution of repeated fixed-horizon trajectory optimization problems of processes that are either too difficult or too complex to be described by physics-based models can pose formidable challenges. Very often, soft-computing methods e.g. black-box modeling and evolutionary optimization are used. These approaches are ineffective or even computationally intractable for searching high-dimensional parameter spaces. In this paper, a structured iterative process is described for addressing such problems: the starting point is a simple parameterization of the trajectory starting with a reduced number of parameters; after selection of values for these parameters so that this simpler problem is covered satisfactorily, a refinement procedure increases the number of parameters and the optimization is repeated. This continuous parameter refinement and optimization process can yield effective solutions after only a few iterations. To illustrate the applicability of the proposed approach we investigate the problem of dynamic optimization of the operation of HVAC (heating, ventilation, and air conditioning) systems, and illustrative simulation results are presented. Finally, the development of advanced communication and interoperability components is described, addressing the problem of how the proposed algorithm could be deployed in realistic contexts.