No abstract

Air conditioning system is a complex system and consumes the most energy in a building. Any fault in the system operation such as cooling tower fan faulty, compressor failure, damper stuck, etc. could lead to energy wastage and reduction in the system’s coefficient of performance (COP). Due to the complexity of the air conditioning system, detecting those faults is hard as it requires exhaustive inspections. This paper consists of two parts; i) to investigate the impact of different faults related to the air conditioning system on COP and ii) to analyse the performances of machine learning algorithms to classify those faults. Three supervised learning classifier models were developed, which were deep learning, support vector machine (SVM) and multi-layer perceptron (MLP). The performances of each classifier were investigated in terms of six different classes of faults. Results showed that different faults give different negative impacts on the COP. Also, the three supervised learning classifier models able to classify all faults for more than 94%, and MLP produced the highest accuracy and precision among all.

Summary There has been an increased recognition in road thermal energy harvesting for the past decades due to the massive waste heat from the asphalt pavement. This study aims to design a thermoelectric energy harvesting system (TEHs) that converts the waste heat from the surface of asphalt pavement into useful electrical energy. The TEHs utilizes the H‐shape element in subterranean cooling in order to achieve a high‐temperature difference (ΔT). In this proposed cooling element method, an aluminum plate was welded in between two 1.25 in. of diameters H‐shape structures, and two cascaded thermoelectric modules (TEM), APH‐127‐10‐25‐S, were placed in between the top plate and bottom plate. The heat transfer analysis for the TEHs is performed using finite element analysis (FEA) simulation and validated with an experimental investigation. Based on simulation results, the H‐shape cooling element has a 75% improvement of ΔT from a single rod cooling element design. Furthermore, using a top plate with 100 × 200 mm dimension, also given an extra 8°C of ΔT than the top plate with a 65 × 200 mm dimension, it appears that the conduction shape factor, S, may have influenced the heat distribution in the cooling element. While, in field testing, the results can corroborate with the simulation where the maximum ΔT has reached a similar ΔT of 23°C, with a maximum relative error of 0.057%. Based on the feasibility studies with an application, the TEHs has effectively fully charged 5 F supercapacitors, within 3 hours, for the use of automatic street lights, which substantiated the significance of TEHs design. The present study represents a new perspective for self‐sustainable TEHs design integrated with high cooling performances of the H‐shape element in subterranean cooling.

This study presents the behavioral model of thermal temperature and power generation of a thermoelectric-solar hybrid energy system exposed to dynamic transient sources. In the development of thermoelectric-solar hybrid energy system, studies have focused on the regulation of both systems separately. In practice, a separate control system affects hardware pricing. In this study, an inverse dynamic analysis shaping technique based on exponential function is applied to a solar array (SA) to stabilize output voltage before this technique is combined with a thermoelectric module (TEM). This method can be used to estimate the maximum power point of the hybrid system by initially shaping the input voltage of SA. The behavior of the overall system can be estimated by controlling the behavior of SA, such that SA can follow the output voltage of TEM as the time constant of TEM is greater than that of SA. Moreover, by employing a continuous and differentiable function, the acquired output behavior of the hybrid system can be attained. Data showing the model is obtained from current experiments with predicted values of temperature, internal resistance, and current attributes of TEM. The simulation results show that the proposed input shaper can be used to trigger the output voltage of SA to follow the TEM behavior under transient conditions.

No abstract