Surabaya Shipbuilding State Polytechnic

Battery management systems are essential in electric vehicles and renewable energy applications, especially in terms of ensuring optimal battery health and performance and regarding the state of charge (SOC) in batteries consisting of many cells. The lifetime and efficiency of the battery depend on the accuracy of the SOC parameter estimation. Moreover, systems that apply active balancing technology are able to move cells with high SOC data to cells with low SOC. Many methods have been developed, but their long execution time makes them less optimal when applied. High-speed SOC estimation is required in active balancing technology, in addition to high accuracy. Therefore, this study proposes the estimation of SOC parameters using a statistical and metaheuristic approach from voltage and current input data in each battery cell. The experimental results showed that the metaheuristic-based method (ANFIS) had better RSME and R2 values compared with the polynomial and linear regression or even the machine learning-based method (recurrent neural network) for training data.

This paper presents a detailed experimental design framework for free-running tests on an amphibious marine craft type N219A, focusing on sensor integration and steering mechanism evaluation during turning circle maneuvers in a free-running pool. The experimental setup employs a scalar model approach combined with propulsion motor drive calculations to replicate realistic operational conditions. Two cost-effective sensors are integrated to capture comprehensive navigational and dynamic data: a GPS ArduPilot sensor provides the trajectory track of the floatplane, while an ADIS 16364 accelerometer outputs sway and surge velocities as well as roll and yaw accelerations. Calibration and data acquisition methods are tailored to optimize the precision of these measurements. The steering mechanism design emphasizes hydrodynamic performance and control responsiveness, with evaluation relying on trajectory and dynamic data from the sensor suite. Results from the free-running tests demonstrate the efficacy of the proposed experimental design in assessing vehicle maneuverability and the interplay between propulsion and steering systems. Limitations such as the measurement constraints of the sensor suite and susceptibility to environmental interference are discussed, providing insights for further improvements. This work establishes a robust experimental framework tailored for amphibious vehicle maneuverability studies, combining affordability with precision measurement techniques. Insights gained highlight critical factors influencing sensor integration and mechanical control effectiveness. Subsequent investigations will focus on implementing multi-sensor data fusion and optimizing propulsion control algorithms to improve experimental accuracy and adaptability in diverse operational environments.

The development of science and technology has experienced a very high acceleration. Along with this, the need for and demand for fast and accurate information is also getting higher. Based on this, this research aims to create an automatic portal model using UHF RFID. In addition, this model will have digital data documenting entry and exit of vehicles, so that it is easier in the process of monitoring data on students, lecturers and guests in carrying out activities within the Madura State Polytechnic (POLTERA) campus. To help security officers, and prevent transmission of Covid-19, an automatic entry and exit control system is needed. The purpose of this research is to design and build an automatic portal with RFID that has Ultra High Frequency (UHF) technology and additional driver body temperature detection technology. The temperature value and the RFID code are read by the RFID Reader and then the code is used as a condition for access to open and close the portal. After that, the recorded data in the form of RFID card data, temperature data, and driver images will be stored in a microSD data logger.

Wind energy has developed rapidly with various efforts aimed at improving its performance. The Darrieus wind turbine will study its performance by adding fins to the surface of the Darrieus turbine. The turbine shape in this study utilizes NACA 0018 symmetry by adding one fin on the mid-span side and the fin is varied against the fin height. The method used is a numerical study with a CFD approach that varies the fin height to determine the value of the torque coefficient, power coefficient, and tip speed ratio. This study uses a Darrieus turbine with a diameter of 40 cm and a rotor height of 50 cm, and varies the fin height by 1.5 cm, 2.5 cm, and 3.5 cm. The results show that the turbine performance increases by 45.23% at a fin height of 2.5 cm.

The development of voice based biometric security systems has increased the demand for authentication methods capable of operating accurately and securely in open set speaker verification scenarios. In this scenario, the system is required not only to recognize registered users but also to reject unknown users who are not included in the system database. This study focuses on hyperparameter optimization in a Convolutional Neural Network Embedding based speaker verification system using Mel Frequency Cepstral Coefficient (MFCC) features and speaker embeddings. The optimization process was conducted through several experimental stages, including MFCC parameter tuning, CNN architecture tuning, embedding dimension tuning, and audio augmentation analysis. The dataset consisted of Indonesian speech recordings from 8 registered speakers and 1 unknown speaker, sampled at 16 kHz under controlled recording conditions. The dataset was divided into training, enrollment, and testing subsets to support open set speaker verification evaluation and reduce data leakage. System performance was evaluated using accuracy, validation loss, False Acceptance Rate (FAR), False Rejection Rate (FRR), best threshold, and inference time. The experimental results show that the best configuration was achieved using the MFCC-C parameters (N_MFCC = 40, N_FFT = 1024, HOP_LENGTH = 256, N_MELS = 40), the CNN-E architecture with three convolution blocks (32-64-128), an embedding dimension of 64, and lightweight augmentation consisting of noise injection, pitch shifting, and time stretching. This configuration achieved stable system performance with a test accuracy of 96.43% and a FAR of 8.7%, while maintaining lightweight computational complexity and real time inference capability. The results also indicate that excessive augmentation may increase embedding overlap between speakers, thereby reducing system security performance. However, the study was conducted on a limited scale dataset and has not yet evaluated robustness against spoofing attacks, replay attacks, or adversarial synthesized voice attacks. Overall, the study indicates that hyperparameter optimization influences the balance between accuracy, computational efficiency, and biometric security performance in lightweight CNN based voice biometric authentication systems under limited scale evaluation conditions.