Chiller Fault Diagnosis Based on Automatic Machine Learning

Abstract

Intelligent diagnosis is an important means of ensuring the safe and stable operation of chillers driven by big data. To address the problems of input feature redundancy in intelligent diagnosis and reliance on human intervention in the selection of model parameters, a chiller fault diagnosis method was developed in this study based on automatic machine learning. Firstly, the improved max-relevance and min-redundancy algorithm was used to extract important feature information effectively and automatically from the training data. Then, the long short-term memory (LSTM) model was used to mine the temporal correlation between data, and the genetic algorithm was employed to train and optimize the model to obtain the optimal neural network architecture and hyperparameter configuration. Finally, a transient co-simulation platform for building chillers based on MATLAB as well as the Engineering Equation Solver was built, and the effectiveness of the proposed method was verified using a dynamic simulation dataset. The experimental results showed that, compared with traditional machine learning methods such as the recurrent neural network, back propagation neural network, and support vector machine methods, the proposed automatic machine learning algorithm based on LSTM provides significant performance improvement in cases of low fault severity and complex faults, verifying the effectiveness and superiority of this method.

Deep learning in fault detection and diagnosis of building HVAC systems: A systematic review with meta analysis

“…The design gating mechanisms and cell states enable the LSTM to perform better in modelling long-term temporal dependencies embedded inside the sequence data [88]. To improve the performance of a vanilla LSTM for HVAC FDD [56] [20] [89] [90], optimization methods such as generic algorithm is used in [58] to optimize learning rate, batch size, etc. As opposed to the optimization, sets of hyperparameters and network structure configurations are hand-crafted and evaluated in [59] to search for the optimal setting, it is also concluded from this study that adding more LSTM neurons or layers potentially causes low convergence speed and overfitting problems.…”

Improving the Efficiency of Fan Coil Units in Hotel Buildings through Deep-Learning-Based Fault Detection

“…Moreover, recurrent networks are essential for analyzing time series data, as they excel in capturing sequential dependencies, processing variable-length sequences, retaining historical information, automatically extracting relevant features, and performing tasks such as prediction and anomaly detection. In this context, recurrent models incorporating long short-term memory network (LSTM) architectures have been studied in detail by Liu et al [ 28 ], Tian et al [ 29 ], Taheri et al [ 30 ], and Behravan et al [ 31 ]. In addition, gated recurrent unit (GRU) models, a special type of RNN, have been proposed and used by Wang et al [ 32 ] and Li et al [ 33 ] in their respective studies.…”

Research on Fault Diagnosis of HVAC Systems Based on the ReliefF-RFECV-SVM Combined Model

“…When chillers malfunction, HVAC systems' efficiency can be reduced by 15-30%, leading to increased energy consumption, poor indoor/outdoor air quality [5], and gradual loss of system functionality. Faults diagnosis in chillers can reduce energy consumption and maintenance costs by 20-50% [6]. Therefore, the fault diagnosis of HVAC systems is critical for energy conservation, cost reduction, emission reduction, and equipment efficiency improvement.…”