Fault detection and diagnosis for heat source system using convolutional neural network with imaged faulty behavior data

Abstract

Faults that impair performance can occur in a heat source system because it comprises various devices and has complex controls. This article presents a novel method for fault detection and diagnosis (FDD). This study focused on a real system with a water thermal storage tank. First, system behaviors in response to faults were determined using a detailed system simulation. Then, a fault database was generated using the simulation results with fault labels. We preprocessed the database and converted the data into images. Then, convolutional neural networks (CNNs) were trained using the database, and the trained CNNs were used for diagnosing real data. The accuracy of the CNNs was 98.7% in training, and real data were diagnosed with probabilities. We analyzed the real data, where the probability indicated the likely presence of a fault and reviewed how the real data were similar to the fault assumed in the simulation. We concluded that the proposed FDD method will help in analyzing real data, as it indicates faults emerging in the real data with probability, whereas conventional data analysis requires checking the data using expert knowledge.

Forecasting of Energy Demands for Smart Home Applications

“…In this section, various HVAC devices are used to find the effectiveness of the proposed method that includes Heating and Cooling Split Systems, Hybrid Split System, Duct Free (Mini-Split), Packaged Heating and Air, Window Through-the-Wall Air Conditioner, Packaged Terminal Heat Pumps, Unit Heaters, Packaged Rooftop Unit, Packaged Rooftop Heat Pump and Humidifiers. The proposed method is compared with other existing methods that include RNN [43][44][45][46], ANN [39,46] and CNN [47][48][49][50] algorithms and with other communications protocols, including Li-Fi, Wi-Fi, Zigbee and Bluetooth. The datasets are collected from large size units, as in [51], and the simulations are conducted in a python anaconda complier with 16GB RAM usage requirements.…”

“…Figure 9 shows improved load balancing accuracy on uncontrollable loads (Packaged Terminal Heat Pumps, Unit Heaters, Packaged Rooftop Unit and Packaged Rooftop Heat Pump and Humidifiers) by Li-Fi technology for smart commercial three-storied buildings with multiple HVAC devices over the RNN [43][44][45][46], ANN [39,46] and CNN [40,[47][48][49][50] algorithms. The results show that an increased number of counts for single device lags the stability due to the reduced load balancing accuracy compared to those Figure 9 shows improved load balancing accuracy on uncontrollable loads (Packaged Terminal Heat Pumps, Unit Heaters, Packaged Rooftop Unit and Packaged Rooftop Heat Pump and Humidifiers) by Li-Fi technology for smart commercial three-storied buildings with multiple HVAC devices over the RNN [43][44][45][46], ANN [39,46] and CNN [40,[47][48][49][50] algorithms. The results show that an increased number of counts for single device lags the stability due to the reduced load balancing accuracy compared to those with fewer device counts.…”

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

“…The CNN model is capable of uncovering experimentally designed incipient fault operations. Miyata et al [259] conducted CNN-based FDD using system data plots directly as model inputs. FFs can be extracted using a data combination process in the pooling layer.…”

Development and application of methods of internal inspection of district heating networks

“…• measurement of stress concentration (metal magnetic memory); • acoustic tomography; and • measurement of the hardness of the base metal and of electric potential [15,16].…”