The Electrochemical Hydrogen Compressor is an optimal device for compressing low-pressure hydrogen to high-pressure hydrogen. It has a similar structure to the Proton Exchange Membrane Fuel Cell but operates at extremely high pressures, requiring multiple cells sealed with End Plates. The End Plate design must provide initial cell activation support, withstand maximum operating pressure within the stack, and prevent internal gas leakage. This study applies a multi-objective optimization method and grey relation analysis to determine the optimal design parameters for the End Plate based on the activation area of Dummy Cells. Finite Element Method (FEM) analysis is conducted to verify the effectiveness of the optimized End Plate design, considering the uniform pressure distribution with stacked Dummy Cells (1, 3, 6, 12). The analysis reveals that the parameters affecting the uniform pressure distribution include the End Plate design, stack sealing pressure, individual Cell design parameters, and the number of Cell stack layers.

Due to recent development of sensor technology and IoT, research is being actively conducted on PHM (Prognostics and Health Management), a methodology that collects equipment or system status information and determines maintenance using diagnosis and prediction techniques. Among various research studies, research on anomaly detection technology that detects abnormalities in assets through data is becoming more important due to the nature of industrial sites where it is difficult to obtain failure data. Conventional machine learning-based and statistical-based models such as PCA, KNN, MD, and iForest involve human intervention in the data preprocessing process. Thus, they are not suitable for time series data. Recently, deep learning-based anomaly detection models with better performances than conventional machine learning models are being developed. In particular, several models with improved performance by fusing time series data with LSTM, AE (Autoencoder), VAE (Variational Auto Encoder), and GAN (Generative Adversarial Network) are attracting attention as anomaly detection models for time series data. In the present study, we present a method that uses Likelihood to improve the evaluation method of existing models.

This study is to numerically investigate the Aero-Acoustics of Turbocharger compressor. The turbocharger compressor is high-speed turbomachinery that rotates faster than 200,000 RPM. The Aero-Acoustics with five different rotational speeds (120,000, 150,000, 180,000, 200,000, and 220,000 RPM) is used herein. The fluid domain is designed by CATIA V5R21 and analyzed by ANSYS FLUENT V19.1 with compressible momentum equation. The Pressure-velocity coupling method of the solver is the coupled algorithm and calculated by a pressure-based method. Numerical analysis of the aero-acoustics by broadband noise sources model provides calculated sound-source and acoustic-level based on steady RANS. At the industrial site, it is important to quickly analyze the noise source. APL (Acoustic Power Level) with five different rotational speeds and sound characteristics based on flow factor at the compressor wheel was numerically calculated for the noise-based design. The maximum APL is located at blade tips in case of 120,000, 150,000 and 180,000 RPM. In the case of 200,000 RPM, the maximum APL is located at splitter tips. At more than 220,000 RPM, the maximum APL is located at the balancing cutting section of the wheel. In order to optimally design the high-speed turbomachinery, cutting sections and side locations of the wheel are essential factors to reduce physical noise.

Inverter-Type refrigerators are known to consume less energy by varying the inverter frequency according to indoor temperatures and refrigerant pressure through indoor-outdoor communication. However, many commercial operators cannot afford to replace indoor units with ones capable of communication. In a non-communication configuration, indoor units are connected with an inverter-type outdoor unit without intercommunication abilities. The research goal is finding appropriate operating parameters to achieve energy efficiency. Thus, an operation algorithm with two modes is proposed, i.e., one to search the best operating parameters and one for normal operation with the best parameters. The experimental evaluation showed 11.27% reduction in energy consumption, indicating a good applicability of the algorithm.