This study explores the implementation of an intelligent energy management system for industrial buildings, leveraging the capabilities of artificial intelligence (AI) technologies. The approach integrates advanced data analytics, machine learning algorithms, and real-time monitoring to optimize energy consumption, enhance operational efficiency, and reduce costs. Key components include the deployment of sensors, implementation of AI-driven optimization algorithms for dynamic control of energy-consuming systems. The system also incorporates demand response strategies, automated control systems, and continuous learning mechanisms to adapt to changing conditions and user behavior. User engagement interfaces are designed to promote energy-efficient practices, and integration with renewable energy sources enhances sustainability. The study highlights the potential for significant cost savings, reduced environmental impact, and improved regulatory compliance through the intelligent management of industrial building energy based on AI technologies. To enhance the efficiency of energy-saving practices in industrial buildings by integrating artificial intelligence technology. This integration is used to analyze and manage the intelligent energy-saving systems in these buildings, ultimately leading to a reduction in energy consumption. The paper delves into the circuit structure, workflow, and functionality of energy-saving systems, explaining how they control electrical equipment and the specific hardware components involved. The paper also employs collected data to create a predictive model for energy consumption. Finally, an intelligent management system for conserving energy in industrial buildings is developed, considering various constraints and optimization criteria. The study's data analysis results indicate that this artificial intelligence-based energy-saving system is effective and has a significant impact on the overall energy management of industrial buildings.

The growth of mushrooms demands a very close monitoring of the environmental factors like temperature, humidity and air quality in order to achieve the best outcome in terms of growth and produce. These parameters are usually difficult to monitor and control manually, which results in decreased productivity and crop losses due to the possibility of human error. The paper gives a proposal of an IoT-based smart environmental management system on the cultivation of mushrooms that would allow automated monitoring, control and remote supervision of the mushroom farming huts. The proposed system combines temperature, humidity, gas, and fire sensors with a NodeMCU microcontroller to measure environmental conditions on the continuous basis. An automated water spraying mechanism and control logic is turned on when the humidity or temperature is out of range of predefined threshold values in order to restore the optimum conditions. This is achieved by enabling the turning on of an exhaust fan in the event of the harmful gases or smoke as well as fire detection turning on the water pump and ventilation system to avoid possible dangerous events. One can also manually operate the system from our mobile device itself as per our need. IoT connectivity transfers sensor data and system status to a mobile application enabling real-time monitoring, alert notifications, and manual control where necessary. The suggested system enhances the efficiency of the cultivation, safety, lowered human intervention, and contributes to sustainable farming practices related to mushroom cultivation as a result of intelligent environmental management.

The rising adoption of clean energy sources, grows the requirement to integrate these sources with electric vehicles (EVs) has led to the emergence of a need for advanced power-electronic interfaces which can ensure high efficiency, reliability and dynamic performance. This paper presents an advanced adopted integrated power electronics interface (IPEI) for EV applications where Bloom Energy and the Bloom Box solid oxide fuel cell (SOFC) system is the clean energy source for battery charging and power supply. The proposed IPEI consists of a bidirectional multidevice interleaved DC/DC converter (BMDIC) and an eight-switch inverter (ESI) to enable an integrated power conversion architecture for traction, regenerative braking, battery charging and grid-interactive operating modes. In the Bloom Box, the interconnected SOFC units are stacked to produce electrical power, and the power-electronic interface, a proposed design, conditions the power before delivering it to the EV battery. To realize current sharing, increase in the effective ripple frequency, reduction in current and voltage ripples, and reduction of passive component size, the BMDIC adopts the phase-shifted interleaved switching. To achieve good powertrain control, indirect field-oriented control (IFOC) using particle swarm optimization (PSO) is used for traction and regenerative braking, whereas dual-loop control is applied for the BMDIC and PWM current control is employed when the battery is being charged and discharged with PI compensators. The simulation and experimental results illustrate superior dynamic response, decreased semiconductor switching stress, decreased current and voltage ripples, improved power factor performance, and decreased input current total harmonic distortion (THD). The integrated architecture also enhances system reliability and the number of components and physical space needed for the EV powertrain.