The global push for sustainable development and lower energy usage has prompted increased interest in using automation and control systems in building infrastructures. These systems are now being investigated in Mozambique to determine their ability to increase energy efficiency. This study focuses on the complex processes of creating, deploying, and assessing these systems which use cutting-edge technology such as sensors, machine learning algorithms, and smart devices. The study includes case studies and experimental results that demonstrate the real-world usefulness of these methods. The capacity of automation and control systems to regulate temperature, lighting, and other energy-intensive components significantly reduces overall energy usage within buildings. Furthermore, these systems can discover and diagnose defects in a building's energy systems, allowing for fast and efficient repair—a critical factor in Mozambique, where energy supply is frequently unstable and maintenance is complex. The results of this study imply considerable energy savings, which will help to reduce the country's carbon footprint and advance sustainable development goals. The combination of advanced technologies, practical effectiveness in real-world scenarios, contextual relevance to Mozambique, a holistic approach, emphasis on timely maintenance, and the promotion of sustainable development make this study unique and valuable in building energy efficiency. In conclusion, this study catalyses the creation and implementation of Building Energy Management Systems in Mozambique by providing relevant insights for policymakers, building owners, and energy managers.

In the green motor vehicle era, fuel cell hydrogen electric vehicles (FCHEVs) are becoming promising alternatives. Thus, ensuring the proper operation of FCHEVs solely depends on advanced energy management systems (EMS). In this light, this work looks deeply into how combining machine learning and physics-based models can make FCHEVs operate effectively through improved EMSs. This study extensively analyzes how machine learning and physics-based models operate together in FCHEV-EMS. It therefore breaks through existing research and identifies insights, challenges, and potential future directions. It also looks closely at how machine learning meets challenges in adapting to real-time and handling changing conditions. To gain a better understanding of these issues, this study further recommends innovative ways to integrate machine learning flexibility within the precision of physics-based modeling. It therefore reveals an intriguing potential for additional study in the world of FCHEV-EMS. It represents the integration of machine learning and physics-based models as a potent technique to deal with EMS difficulties and accelerate advances in FCHEV energy management. In the end, it outlines significant findings, addressing why this integrated strategy is crucial in making FCHEVs a world-leading sustainable means of transportation. Through its comprehensive review and strategic perspectives, this initiative aims at catalyzing innovations that actively contribute to the sustainable advancement of FCHEVs.

Driving is one of the prominent necessities of any individual. Due to the growth of the population, transportation has become tight, thus increasing the risk of accidents. There are several reasons that have been highlighted for such accidents, namely, long-distance driving without appropriate relaxation, driving at night, using mobile devices while driving, and driving under the influence of alcohol. Even though several pieces of research are available on automatic braking, this research specifically analyzes the importance of real-time data, while the system is driver-assisted. This research comprised an ultrasonic sensor, speed sensor, Arduino UNO Board, rain sensor, DC actuator, air compressor, and air reservoirs along with the major elements of the braking system. The results were analyzed in three various situations in wet and dry conditions. In addition, 1m of tolerance was provided for the internal adjustments of the vehicle. At first sight, if the distance between the object and the vehicle is larger than the braking distance tolerance limit, the system functions normally where activation is unnecessary. If the distance between the vehicle and the object interface is less than the braking distance tolerance limit, using the sensing mechanism, the brakes will be actuated and the vehicle will stop immediately. Finally, when the vehicle and object are too close, the system will not function again while giving a warning sign for the driver to steer in the proper direction. Overall, the variation in braking distance concerning vehicle speed was analyzed in both wet and dry conditions. Indeed, the research results provided a practically applicable automatic braking system with the driver’s control. This proactive method of accident mitigation represents a novel solution with the future scope of coordinating the automated braking system with a speed reduction system by regulating the accelerator's rotation.

Dynamometers are specifically designed for the measurement of the engine’s brake power. Although several types are physically available, disc brake dynamometers stand out as a more accurate and easily manipulable system. This paper aims to develop a highly accurate disc brake dynamometer while establishing the relationships between several process parameters. In the methodology, the initial stage was to measure the force requirements to the accelerator, brake lever, and clutch. A 3D model was developed using AutoCAD and the necessary accessories were identified. A CG125 engine was selected for the study. The most relevant preliminary design stages were formulated before the experimentation. An interface was added to display the outcome of the analysis. In the results, a real-time graphical relationship was built for brake power and engine speed. Seven sets of data in two different circumstances were obtained. The obtained results were validated against previous experimental results. Both sets of results were matched in most situations for the selected engine. The variation was comparatively less. The engine RPM was stipulated between 2000 and 8000, with the maximum power at the upper limit. The developed domestic application provided major benefits such as the control of the system at a single location, the automatic generation of relationships between the concerned parameters, the presence of a safety switch that can immediately halt the process in emergencies, the use of lambda sensors for corrections, and less maintenance. In terms of limitations, the system is limited to a permanent engine. Thus, this research can be further improved upon with the use of several engines at a time. Errors concerning the software can be avoided with comparative studies. Indeed, this dynamometer's precision and safety were improved more than any other type of conventional disc brake dynamometer.

In this work, we propose an Artificial Intelligence (AI)-based methodology to learn the buckled configuration of stiffeners 3D-printed onto a pre-stretched soft membrane. The membrane acts as a muscle and, if properly pre-deformed, leads to the buckling of the stiffeners so that the resulting configuration can provide new system functionalities. Fused deposition modeling was carried out through a Voron 2.4 3D printer, specifically calibrated for PLA printing on a Lycra fabric. The printed PLA allows a controlled deformation of the substrate–stiffener system; different patterns or stiffeners geometries were investigated, to better understand their effects on the buckled configuration. A finite element model was then set to numerically reproduce the results obtained in the experimental campaign; to catch at best the outcomes, in terms of out-of-plane deflection in the buckled mode, an inverse problem was solved to tune the (nonlinear) constitutive models adopted for PLA and Lycra. Since the numerical model proved to be excessively time-consuming, a surrogate was developed by way of deep learning. In the first stage, YOLO (You Only Look Once) was used and trained properly for feature selection: different geometries of the stiffeners were allowed for and their classification was carried out, in addition to the numerical estimation of their relevant features related to the in-plane geometry. In the second stage, a regression part was added to the AI-based tool to learn the out-of-plane deflection, handled as a label in the learning stage. The results testify to the capability of the proposed approach and its efficiency for subsequent use in the shape optimization of the 3D-printed geometry to attain specific targets of coupled system response.