International Journal of Artificial Intelligence & Robotics (IJAIR)

PCA and Health Indicators: Predicting Machine Failures Through Resistance Analysis

Ayu Dian Hartati, Katherin Indriawati, Simion Sitepu — Sat, 30 Nov 2024 21:33:06 +0700

Predictive maintenance is crucial for ensuring industrial equipment's reliability and operational efficiency. This research aims to develop accurate health indicators to monitor real-time equipment conditions based on current signals. The methodology involves several key stages: collection of degradation data in current signals, data processing and mining, analysis using Principal Component Analysis (PCA), and development of health indicators. This study presents a comprehensive approach to converting raw degradation data into meaningful health indicators for effective engine prognostics and health management (PHM). Leveraging current signal data, we apply data mining and processing techniques to extract statistically significant features, including Standard Deviation, Peak to Peak, Root Mean Square (RMS), Crest Factor, Impulse Factor, Margin Factor, and Kurtosis. PCA is then used to reduce the dimensionality of the processed data, highlighting the principal components that capture the most significant variance indicating the machine's health. The resulting health indicators, derived from PCA, show a clear correlation between changes in additional load and increasing trends of PCA components and health indicators, thus validating the effectiveness of this approach in monitoring and predicting machine conditions. This methodology provides a robust real-time machine health assessment framework, facilitating timely maintenance and reducing the risk of unexpected failures. The results show that increasing resistance over time (t) leads to improved health indicators in a nonlinear manner, providing valuable insights for timely intervention before critical failure occurs. This analysis demonstrates a strong correlation between daily incremental resistance changes and machine condition as monitored by PCA and health indicators. Consistent upward trends in PCA scores and health indicators validate the effectiveness of this technique in tracking engine health under varying resistance conditions.

Cloud Architectures for Distributed Serverless Computing: A Review of Event-Driven and Function-as-a-Service Paradigms

Hewa Majeed Zangana, Zina Bibo Sallow, Marwan Omar — Sat, 30 Nov 2024 21:37:20 +0700

The advent of serverless computing has revolutionized the cloud computing landscape, providing scalable, cost-effective, and flexible solutions for modern application development. This paper comprehensively reviews cloud architectures for distributed serverless computing, focusing on event-driven and Function-as-a-Service (FaaS) paradigms. This research explores the fundamental principles and benefits of serverless computing, highlighting its impact on development practices and infrastructure management. The review covers key components, including orchestration, scalability, and security, and examines leading serverless platforms and frameworks. Through critically analyzing current research and industry practices, identify challenges and propose future directions for optimizing serverless architectures. This paper aims to explain how event-driven and FaaS paradigms reshape cloud computing, enabling developers to build resilient and efficient applications without server management. Our research found that event-driven architectures in serverless computing offer significant advantages in scalability, real-time processing, and resource utilization. FaaS paradigms provide modularity, granularity, and cost-effectiveness, making them suitable for various applications. Cloud-edge collaborative architectures are crucial for achieving low-latency and high-performance serverless applications but require robust security, privacy, and resource management frameworks.

The Implementation of a Smart Energy System with IoT Concept for River Water Distribution Pumps in Rainfed Agricultural Areas

Sat, 07 Dec 2024 21:14:09 +0700

Water pumps for irrigating rainfed rice fields are typically located near or at the edge of rivers, for example, in several locations in Bulakelor and Luwunggede, Brebes Regency villages. Similar situations are found in some rice fields in Sendangadi, Mlati, Sleman, and Piyungan, Bantul, where irrigation pumps are near or at the edge of rivers. According to residents, this reduces the suction power needed. Unfortunately, this also affects the terrain, making it damp and the roads muddy and even slippery, which makes the journey to the pump location difficult and risky, like slipping into a river when the ground is wet and slippery. There is a need to solve this problem by creating an automated pump system that implements IoT concepts using microcontrollers and other control components. The manual water pump is replaced with an electric pump to simplify operation. Control is carried out remotely using a mobile application accessible via websites or smartphones, allowing users to monitor pump operations such as usage duration, automatic on/off scheduling, pump status, and more. This reduces the risk of work accidents with the conventional system. A Renewable Energy System (RES) using a solar power plant (PLTS) is also applied to anticipate power outages, ensuring the IoT system continues to operate and irrigation remains manageable. The operation of such pumps still uses conventional methods that require direct human labor, and only specific individuals can operate the pumps. One example is using diesel pumps that are started by cranking, which requires significant physical strength. These pumps are typically managed collectively by the residents, who take turns operating the pump. Another factor is the age of the pump engine itself, which affects its lifespan. The usage is often not well controlled, with uncertainty in the operating times and operator negligence, such as forgetting to turn off the pump. The limitation of this research is that the operation is conducted automatically based on previous pump usage data, ignoring the size of the pipes used in irrigation and focusing on simplifying the operation of the water pump. The system was installed in rainfed fields in Pagergunung hamlet, where farmers used it to operate water pumps via smartphones with the Ubidots application installed and logged in. The results showed that two farmer groups found the automated pump system helpful. The system was built with several components, including the ESP8266 microcontroller, a rain sensor, a relay/power switch, and other supporting components. The system operates automatically according to the morning operational schedule, and operators from each farmer group can control the pump remotely. The pump operates automatically at 6:00 AM, 6:30 AM, and 7:00 AM. If the rain sensor does not detect water drops/rain, the pump will typically run for 1.5 hours. The innovation in this research lies in implementing an automated pump system that operates according to a schedule while allowing remote control of the pump to irrigate rainfed fields.

Filter Feature Selection for Detecting Mixture, Total Phenol, and pH of Civet Coffee

Shinta Widyaningtyas, Muhammad Arwani, Sucipto Sucipto, Yusuf Hendrawan — Sat, 28 Dec 2024 16:37:39 +0700

Civet coffee, a highly valued specialty coffee, is susceptible to adulteration with regular coffee, resulting in economic losses and consumer fraud. This study investigates the potential of electrical spectroscopy as a non-destructive technique for detecting civet coffee adulteration. We analyzed the bioelectrical properties of civet coffee beans and their mixtures with regular coffee, focusing on impedance parameters (Z, Lp, Ls, Rp, Rs) as potential indicators of adulteration. Two machine learning models, Artificial Neural Network (ANN) and Random Forest, were trained and evaluated using Mean Squared Error (MSE) validation to identify the most informative features for predicting mixture composition, total phenol content, and pH. The findings demonstrate that impedance parameters, particularly Z, consistently exhibited high feature importance scores across different attribute evaluators and search methods. The optimal model, an ANN with a correlation attribute evaluator and ranker search method, achieved an MSE validation of 0.0479, indicating strong predictive accuracy. These results suggest that electrical spectroscopy, coupled with machine learning, offers a promising approach for developing automated, non-invasive methods for detecting civet coffee adulteration, thereby protecting consumers and ensuring the integrity of the specialty coffee market.

Development Of Smart pH Prototype with FTTH Network Integration for Smart Chemistry Laboratory

Muhamad Dzikri Danuarteu, Ahmad Fauzi — Tue, 31 Dec 2024 10:20:23 +0700

Chemistry laboratories at the secondary education level have a vital role in supporting learning and research. However, manual management often faces obstacles in efficiency, accuracy, and data accessibility. Following the Regulation of the Minister of National Education Number 24 of 2007, pH meters are mandatory equipment in high school chemistry laboratories. However, conventional tools are often inadequate for precise real-time measurements. This study developed a Smart pH system integrating the Internet of Things (IoT) and fiber-to-the-home (FTTH) technology for real-time pH measurement. This system was designed using a pH-4502C sensor, Arduino Uno, NodeMCU ESP8266, and Arduino Cloud and tested on five types of solutions relevant to the high school chemistry curriculum, including salt solution, vinegar, lime, liquid soap, and mineral water. The test results showed an average accuracy of 99% and a 1-1.6 seconds data transmission delay. The total loss of the FTTH network was 3.65 dB, within the ITU-T G.984 standard limit. This research supports the fulfillment of national standards and improves the efficiency and reliability of pH measurements, opening up opportunities for further innovation in chemistry education laboratory automation in Indonesia.