In this study, mobile phones, wearable devices, temperature and human motion detectors are integrated as smart sensors for enabling smart air conditioning control. Smart sensors obtain feedback, especially occupants’ information, from mobile phones and wearable devices placed on human body. The information can be used to adjust air conditioners in advance according to humans’ intentions, in so-called intention causing control. Experimental results show that the indoor temperature can be controlled accurately with errors of less than ±0.1 °C. Rapid cool down can be achieved within 2 min to the optimized indoor capacity after occupants enter a room. It’s also noted that within two-hour operation the total compressor output of the smart air conditioner is 48.4% less than that of the one using On-Off control. The smart air conditioner with wearable devices could detect the human temperature and activity during sleep to determine the sleeping state and adjusting the sleeping function flexibly. The sleeping function optimized by the smart air conditioner with wearable devices could reduce the energy consumption up to 46.9% and keep the human health. The presented smart air conditioner could provide a comfortable environment and achieve the goals of energy conservation and environmental protection.

In this study, information pertaining to the development of artificial intelligence (AI) technology for improving the performance of heating, ventilation, and air conditioning (HVAC) systems was collected. Among the 18 AI tools developed for HVAC control during the past 20 years, only three functions, including weather forecasting, optimization, and predictive controls, have become mainstream. Based on the presented data, the energy savings of HVAC systems that have AI functionality is less than those equipped with traditional energy management system (EMS) controlling techniques. This is because the existing sensors cannot meet the required demand for AI functionality. The errors of most of the existing sensors are less than 5%. However, most of the prediction errors of AI tools are larger than 7%, except for the weather forecast. The normalized Harris index (NHI) is able to evaluate the energy saving percentages and the maximum saving rations of different kinds of HVAC controls. Based on the NHI, the estimated average energy savings percentage and the maximum saving rations of AI-assisted HVAC control are 14.4% and 44.04%, respectively. Data regarding the hypothesis of AI forecasting or prediction tools having less accuracy forms Part 1 of this series of research.

The study investigates the development of sensors, in particular the use of thermo-fluidic sensors and occupancy detectors, to achieve smart operation of air conditioning systems. Smart operation refers to the operation of air conditioners by the reinforcement of interaction to achieve both thermal comfort and energy efficiency. Sensors related to thermal comfort include those of temperature, humidity, and pressure and wind velocity anemometers. Improvements in their performance in the past years have been studied by a literature survey. Traditional occupancy detection using passive infra-red (PIR) sensors and novel methodologies using smartphones and wearable sensors are both discussed. Referring to the case studies summarized in this study, air conditioning energy savings are evaluated quantitatively. Results show that energy savings of air conditioners before 2000 was 11%, and 30% after 2000 by the integration of thermo-fluidic sensors and occupancy detectors. By utilizing wearable sensing to detect the human motions, metabolic rates and related information, the energy savings can reach up to 46.3% and keep the minimum change of predicted mean vote (∆PMV→0), which means there is no compromise in thermal comfort. This enables smart air conditioning to compensate for the large variations from person to person in terms of physiological and psychological satisfaction, and find an optimal temperature for everyone in a given space. However, this tendency should be evidenced by more experimental results in the future.

Real-time, non-intrusive and non-destructive process monitoring of micromoulding has been performed using novel ultrasonic sensors integrated onto the barrel and mould insert with an ultrasonic pulse-echo technique. The relative variation of the polymer melt temperature inside the extrusion barrel can be obtained using the ultrasonic velocities of the melt measured at the barrel during extrusion. Melt flow arrival in the mould, and solidification, shrinkage and detachment of the polymer inside the mould cavity are also successfully monitored. The presented ultrasonic sensors and technique enable optimizing the micromoulding process, and improving quality of the moulded parts and process efficiency.

Over the last 50 years since Whittingham created the world’s first lithium-ion battery (LIB) in 1970, LIBs have continued to develop and have become mainstream for electric vehicle (EV) batteries. However, when an LIB for an EV reaches 80% of its state of health (SOH), although it still retains about 80% of its capacity, it is no longer suitable for use in general EVs and must be retired. This is problematic because not only is a retired LIB still viable for use and not totally obsolete, if not properly disposed of, a retired LIB may cause environmental pollution on top of being a waste of resources. Therefore, the reuse of retired LIBs from EVs is increasingly important. This paper uses circular economy (CE) and extended producer responsibility (EPR) as a theoretical basis to deal with the disposal of retired LIBs from EVs in Taiwan from legal, technical, and economic perspectives, and hopes to provide suggestions for the reuse of retired LIBs from EVs in Taiwan.

The air‐conditioning systems have become an indispensable part of our daily life for keeping the quality of life. However, to improve the thermal comfort and reduce energy consumption is crucial to use the air conditioners effectively with rapid development of artificial intelligence technology. This study explored the correlation between the response of human physiological parameters and thermal sensation voting (TSV) to evaluate the comfort level among various cold and hot stimulations. The variations of the three physiological parameters, which were body surface temperature, skin blood flow (SBF), and sweat area on the skin surface, and TSV values were all positively correlated with the stimulation amount under the stimulation of cold wind, hot wind, and heat radiation, but the relationship was not completely linear. Among the three physiological parameters, the forehead skin temperature has the closest relationship with TSV, followed by the SBF and sweat. Among three stimulations, the cold wind stimulation causes the closest relationship between TSV and forehead temperature, followed by the radiation and hot wind stimulations. Through three different machine learning models, namely, random forest (RF) model, support vector machine (SVM) model, and neural network (NN) model, the stimulation of cold wind, hot wind, and heat radiation was applied to investigate the variation of the three physiological parameters as the input of the models. Moreover, the models were evaluated and verified by TSV. The results revealed that among the three different machine learning methods, RF had the best accuracy. The established thermal comfort models can predict the real‐time user’s thermal comfort feeling, so that air‐conditioning equipment’s performance can be optimized to create a healthy and energy‐saving comfortable environment.