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

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%.

Life Cycle Assessment of an Electric Chiller Integrated with a Large District Cooling Plant

District cooling (DC) systems have recently proven to be more economically and environmentally viable as compared to conventional cooling techniques. In most DC setups, electric centrifugal chillers (ECCs) are installed to provide chilled water (CW) to charge the thermal energy storage (TES) tank or for direct CW supply to the DC network. The operation of these ECC systems consumes most of the electrical power supplied to the entire DC plant; this therefore strengthens the need to conduct a comprehensive environmental assessment in order to quantify the indirect ecological impact resulting from the energy consumed in the ECC system operation. In order to achieve this, a case study was conducted of four ECC systems with a use-life of 25 years installed in a large DC plant in Malaysia. A gate-to-gate life cycle assessment (LCA) methodology was adopted to analyze the environmental performance of the system setup. The result of the study year reveals that April and June account for the highest and lowest environmental impact, respectively. The influence of climatic temperature conditions on the monthly cooling and environmental load distribution was also observed from the results. Finally, in substantiating the study’s investigation, environmental performance based on the composition of two different electricity fuel mixes is discussed and compared. The results revealed a drastic decrease in environmental load as the ratio of non-renewable energy sources decreased in the composition of the mix, thereby reducing the contribution of the overall environmental impact of the ECC systems’ use phase.