Incipient Chiller Fault Diagnosis Using an Optimized Least Squares Support Vector Machine With Gravitational Search Algorithm

Abstract

Operational faults in centrifugal chillers will lead to high energy consumption, poor indoor thermal comfort, and low operational safety, and thus it is of significance to detect and diagnose the anomalies timely and effectively, especially for those at their incipient stages. The least squares support vector machine (LSSVM) has been regarded as an effective algorithm for multiclass classification. One of the most difficult issues in LSSVM is parameter tuning. Therefore, this paper reports a development of a gravitational search algorithm (GSA) optimized LSSVM method for incipient fault diagnosis in centrifugal chillers. Considering the inadequacies of conventional principle component analysis (PCA) algorithm for nonlinear data transformation, kernel principle component analysis (KPCA) was firstly employed to reduce the dimensionality of the original input data. Secondly, an optimized “one against one” multi-class LSSVM classifier was developed and its penalty constant and kernel bandwidth were tuned by GSA. Based on the fault samples of seven typical faults at their incipient stages in chillers from ASHRAE RP 1043, the proposed GSA optimized LSSVM fault diagnostic model was trained and validated. For the purpose of demonstrating the priority of the proposed fault diagnosis method, the obtained results were compared to that of using the LSSVM classifier optimized by another two algorithms, namely, the conventional cross-validation method and particle swarm optimizer. Results showed that the best fault diagnosis performance could be achieved using the proposed GSA-LSSVM classifier. The overall average fault diagnosis accuracy for the least severity faults was reported over 95%.

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

“…As depicted in Figure 11, the Relief-RFECV feature subset achieves higher accuracy than other feature sets in the 1DCNN-BIGRU, KNN, RF, and SVM fault models, thus confirming the superiority of the feature selection algorithm. In addition, the Relief-RFECV-SVM method was compared with other proposed fault diagnosis methods (Bayesian network merged distance rejection (DR-BN) [40], kernel principle component analysis-least squares support vector machine-gravitational search algorithm (KPCA-LSSVM-GSA) [41], random forest-global sensitivity analysis-cascade feature cleaning and supplement (RF-GSA-CFCS) [21], one-dimensional convolutional neural network-bidirectional gated recurrent unit (1DCNN-BIGRU) [42] and 1DCNN [18]). As shown in Figure 12 and Table 11, the proposed method achieved higher fault In addition, the Relief-RFECV-SVM method was compared with other proposed fault diagnosis methods (Bayesian network merged distance rejection (DR-BN) [40], kernel principle component analysis-least squares support vector machine-gravitational search algorithm (KPCA-LSSVM-GSA) [41], random forest-global sensitivity analysis-cascade feature cleaning and supplement (RF-GSA-CFCS) [21], one-dimensional convolutional neural network-bidirectional gated recurrent unit (1DCNN-BIGRU) [42] and 1DCNN [18]).…”

Loss Prediction of Ultrahigh Voltage Transmission Lines Based on EEMD–LSTM–SVR Algorithm

“…As for the algorithm selection in model construction, in recent years, based on the large amount of data generated by the operation of the power system and the development of artificial intelligence algorithms, traditional line loss calculation methods have gradually developed to intelligent processing algorithms represented by artificial neural networks (Zhang et al, 2018). The least squares support vector machine (LSSVM) can be used for both classification and prediction Chen et al, 2021;Xia et al, 2021). The support vector regression (SVR) improves the LSSVM, which significantly increases the speed of operation (Liu et al, 2019).…”