Machine learning predictive models for optimal design of building-integrated photovoltaic-thermal collectors

This research article aims to examine the feasibility of several machine learning techniques to forecast the exergetic performance of a building-integrated photovoltaic-thermal (BIPVT) collector. In this regard, it uses multiple linear regression, multilayer perceptron, radial basis function regressor, sequential minimal optimization improved support vector machine, lazy.IBK, random forest (RF), and random tree approaches. Moreover, it implements the performance evaluation criteria (PEC) to evaluate the system's performance from the perspective of exergy. The use of these approaches serves the identification process to realize the relationship between the input–output parameters of the BIPVT system. The novelty of this work is that it utilizes and compares multiple learning algorithms to predict the PEC of BIPVT through design parameters. Hence, the research considers the parameter (PEC) as the essential output of the BIPVT collector, while the input parameters are the length, width, and depth of the duct, located under the PV modules, as well as the air mass flow rate. The results of the research for the statistical indexes of mean absolute error, root mean square error, relative absolute error (%), and root relative squared error (%) show values of (0.2967, 0.3885, 1.8754, and 1.5237) and (0.4957, 0.8153, 2.9586, and 2.8289), respectively, for the training and testing datasets. While R² ranges (0.9997-0.9999) for those datasets. Therefore, to estimate the exergy performance of the BIPVT collector, the RF model is superior to other proposed models.     

A review of solar energy modeling techniques

Solar radiation data provide information on how much of the sun's energy strikes a surface at a location on the earth during a particular time period. These data are needed for effective research in solar-energy utilization. Due to the cost of and difficulty in solar radiation measurements and these data are not readily available, alternative ways of generating these data are needed. In this paper, a review is made on the solar energy modeling techniques which are classified based on the nature of the modeling technique. Linear, nonlinear, artificial intelligence models for solar energy prediction have been considered in this review. The outcome of the review showed that the sunshine ratio, ambient temperature and relative humidity are the most correlated coefficients to solar energy.     

Techno-economical assessment of grid connected PV/T using nanoparticles and water as base-fluid systems in Malaysia

In this study, the techno-economic assessment of GCPVT with nanofluid has been investigated based on theoretical and experimental work in Malaysia. The productivity and utilisation of the PV have been investigated using yield and capacity factors (CFs), respectively. Also, the cost of energy and payback period has been calculated. The system installed, tested, and data have been collected. Evaluation of the system in terms of current, voltage, power and efficiency are presented. The average daily ambient temperature and total global solar energy in Kuala Lumpur are 38.89°C and 4062?Wh/m², respectively. MATLAB software is used to analyse the measured data. The assessment results show that the GCPVT system has annual yield factor, CF, the cost of energy; payback period, and efficiency are (128.34–183.75)?kWh/kWp, (17.82–25.52)%, 0.196?USD/kWh, 7–8 years and 9.1%, respectively. This study indicates that the GCPVT system with nanofluid improved the PV technical and economic performance.     

Review of solar assisted heat pump drying systems for agricultural and marine products

Combining solar energy and heat pump technology is a very attractive concept. It is able to eliminate some difficulties and disadvantages of using solar dryer systems or solely using heat pump drying separately. Solar assisted heat pump drying systems have been studied and applied since the last decades in order to increase the quality of products where low temperature and well-controlled drying conditions are needed. This paper reviewed studies on the advances in solar heat pump drying systems. Results and observation from the studies of solar assisted heat pump dryer systems indicated that for heat sensitive materials; improved quality control, reduced energy consumption, high coefficient of performance and high thermal efficiency of the dryer were achieved. The way forward and future directions in R&D in this field are further research regarding theoretical and experimental analysis as well as for the replacement of conventional solar dryer or heat pump dryer with solar assisted heat pump drying systems and solar assisted chemical and ground source heat pump dryers which should present energy efficient applications of the technologies.     

Review on solar-driven ejector refrigeration technologies

The objective of this paper is to provide a literature review on solar-driven ejector refrigeration systems and to give useful guidelines regarding background and operating principles of ejector. The development history and recent progress in solar-driven ejector refrigeration systems are reported and categorized. It shows that solar-driven ejector refrigeration technologies are not only can serve the needs for cooling requirements such as air-conditioning and ice-making and medical or food preservation in remote areas, but also can meet demand for energy conservation and environment protection. For these reasons, the research activities in this sector are still increasing to solve the crucial points that make these systems not yet ready to compete with the well-known vapour compression system. However, a lot of research work still needs to be done for large-scale applications in industry and for the replacement of conventional refrigeration machines.     

A new spatio-temporal background–foreground bimodal for motion segmentation and detection in urban traffic scenes

Neural Computing and Applications - Automatic vehicle detection in urban traffic surveillance is an important and urgent issue, since it provides necessary information for further processing....     

Phytosterols and their extraction from various plant matrices using supercritical carbon dioxide: a review

Phytosterols provide important health benefits: in particular, the lowering of cholesterol. From environmental and commercial points of view, the most appropriate technique has been searched for extracting phytosterols from plant matrices. As a green technology, supercritical fluid extraction (SFE) using carbon dioxide (CO₂) is widely used to extract bioactive compounds from different plant matrices. Several studies have been performed to extract phytosterols using supercritical CO₂ (SC‐CO₂) and this technology has clearly offered potential advantages over conventional extraction methods. However, the efficiency of SFE technology fully relies on the processing parameters, chemistry of interest compounds, nature of the plant matrices and expertise of handling. This review covers SFE technology with particular reference to phytosterol extraction using SC‐CO₂. Moreover, the chemistry of phytosterols, properties of supercritical fluids (SFs) and the applied experimental designs have been discussed for better understanding of phytosterol solubility in SC‐CO₂. © 2014 Society of Chemical Industry     

Microbial community analysis of mixed anaerobic microflora in suspended sludge of ASBR producing hydrogen from palm oil mill effluent

This study investigated the microbial community of an anaerobic sequencing batch reactor (ASBR) operating at mesophilic temperature under varying hydraulic retention times (HRTs) for evaluating optimal hydrogen production conditions, using palm oil mill effluent (POME) as substrate. POME sludge enriched by heat treatment with hydrogen-producing bacteria was used as inoculum and acclimated with the POME. The microbial community was determined by first isolating cultivable bacteria at each operating HRT and then using polymerase chain reaction (PCR). The PCR products were sequenced and sequence identification was performed using the BLAST algorithm and Genbank database. The findings revealed that about 50% of the isolates present were members of the genus Streptococcus, about 30% were Lactobacillus species and around 20% were identified as species of genus Clostridium. Scanning electron microscopy (SEM) analysis also confirmed the presence of spherical and rod-shaped microbial morphologies in the sludge samples of bioreactor during prolonged cultivation.     

Bioactive compounds and advanced processing technology: Phaleria macrocarpa (sheff.) Boerl,a review

Recent technological advances and the development of new methods has provided an opportunity to obtain highly purified natural bioactive compound extracts with potential for the treatment and prevention of human diseases. The use of hazardous and toxic solvents for the extraction and processing of bioactive compounds from plant materials is considered a problem for health, safety and environmental pollution. Advanced technology aims to increase production of the desired compounds and find an alternative to using toxic solvents in the extraction of bioactive compounds from plant materials. The ever growing interest in plant bioactive compounds and today's concerns about environment issues have led to an increased need for an efficient and green extraction method. This review is focused on the extraction of bioactive compounds from plants using advanced and environment‐friendly methods such as supercritical fluid extraction, microwave‐assisted extraction, ultrasound‐assisted extraction and similar techniques that can extract rapidly and free from organic residues. An updated overview of the bioactive compounds present in the plant Phaleria macrocarpa and its extraction, fractionation, purification and isolation is provided. The advantages and disadvantages of both conventional and non‐conventional extraction methods are also discussed in this review. © 2014 Society of Chemical Industry     

Performance of a non-metallic unglazed solar water heater with integrated storage system

The performance of a new design of non-metallic unglazed solar water heater integrated with a storage system has been studied. In this system, the collector and storage were installed in one unit. All parts of the system have been fabricated from fiberglass reinforced polyester (GFRP) using a special resin composition that provides good thermal conductivity and absorptivity. The storage tank has a capacity of 329 l. The design of the storage system was sandwich construction, with the core material made out of polyurethane foam, which combines stiffness and lightness of structure with very good thermal insulation. The width and length of the absorber plat were 1.4 and 1.8 m, respectively. The performance of the system has been investigated by two methods. In the first method, the storage tank was filled up with water the night before the test. The tank was then drained during the night, refilled and made ready for the next day’s test. The tests were repeated under varied environmental conditions for several days. The maximum water temperature in the storage tank of 63 °C has been achieved for a clear day operation at an average solar radiation level of 700 W m⁻² and ambient temperature of 30 °C. The decrease of water temperature with and without the thermal diode is 10 and 20 °C, respectively. In the second method, the testing was of the same way, but in this case without draw-off or draining of the hot water from the storage tank. All data readings were recorded from sunrise to sunset over the same period. The temperature was recorded for several days and ranges of 60–63 °C were obtained in the storage tank. A system efficiency of 45% was achieved at an average solar radiation level of 635 W m⁻² and ambient temperature of 31 °C.