Fault Diagnosis of DCV and Heating Systems Based on Causal Relation in Fuzzy Bayesian Belief Networks Using Relation Direction Probabilities

Abstract

The state-of-the-art provides data-driven and knowledge-driven diagnostic methods. Each category has its strengths and shortcomings. The knowledge-driven methods rely mainly on expert knowledge and resemble the diagnostic thinking of domain experts with a high capacity in the reasoning of uncertainties, diagnostics of different fault severities, and understandability. However, these methods involve higher and more time-consuming effort; they require a deep understanding of the causal relationships between faults and symptoms; and there is still a lack of automatic approaches to improving the efficiency. The data-driven methods rely on similarities and patterns, and they are very sensitive to changes of patterns and have more accuracy than the knowledge-driven methods, but they require massive data for training, cannot inform about the reason behind the result, and represent black boxes with low understandability. The research problem is thus the combination of knowledge-driven and data-driven diagnosis in DCV and heating systems, to benefit from both categories. The diagnostic method presented in this paper involves less effort for experts without requiring deep understanding of the causal relationships between faults and symptoms compared to existing knowledge-driven methods, while offering high understandability and high accuracy. The fault diagnosis uses a data-driven classifier in combination with knowledge-driven inference with both fuzzy logic and a Bayesian Belief Network (BBN). In offline mode, for each fault class, a Relation-Direction Probability (RDP) table is computed and stored in a fault library. In online mode, we determine the similarities between the actual RDP and the offline precomputed RDPs. The combination of BBN and fuzzy logic in our introduced method analyzes the dependencies of the signals using Mutual Information (MI) theory. The results show the performance of the combined classifier is comparable to the data-driven method while maintaining the strengths of the knowledge-driven methods.

Mutual Knowledge Analysis of Music Online Communication and Contemporary People’s View of Music Based on Gray Correlation Analysis and Knowledge-Driven

“…Since the network is a whole, music data in the network environment can be disseminated in various service forms [ 3 ]. First of all, most network music dissemination in China is free; as long as users have network terminals, they can access music resources on the network, and listeners can also download and collect music and repeat and listen to it, which makes the scope of music dissemination more extensive and promotes the dissemination and development of music [ 4 ]. Secondly, network transmission has freedom, network environment has the form of resource sharing, and people can get music without the restriction of geography, time, and so on, thus providing a broader space for the spread of music [ 5 ].…”

Realistic Simulation of Sensor/Actuator Faults for a Dependability Evaluation of Demand-Controlled Ventilation and Heating Systems

“…Each room is typically equipped with multiple electronic components, such as sensors and actuators. The HVAC model in this paper is based on the heating and natural ventilation in the winter time, while the outdoor temperature range is lower than the indoor temperature [23].…”

“…Here, in this paper, the following component faults are applied to our proposed fa injection that are modeled for sensors and actuators values as follow [25]: 2).  Heater actuator (thermostat) fault: This fault describes a stuck-at fault when heater sticks to a specific position (off/on).…”

“…Some researchers developed simulation-based fault injection system models. Behravan et al [21][22][23] implemented simulation-based fault injection models for demand-controlled ventilation (DCV) and heating systems in multi-zone office buildings. In [21], Behravan et al extended the simulated HVAC system models, providing them with FI capabilities of permanent stuck-at faults for the sensors, stuck-at opened/closed damper actuators, and stuck-at heater actuators.…”

“…Behravan et al [24] also introduced a command-based fault injection framework in a compositional model in Matlab whereas the codes are connected to the simulation blocks in Simulink. Further, Behravan et al [25] proposed an automated FI tool to systematically inject different faults with different fault injection times. An overview of the SiFI techniques is provided and summarized in Table 1.…”