As industrial systems grow larger and more interconnected, timely fault detection is essential to minimize downtime, enhance reliability, reduce costs. However, conventional methods focus on reactive maintenance, limiting their ability detect faults before escalation. Additionally, propagation in large-scale can degrade performance. To address these challenges, we propose an auto-associative shared nearest neighbor kernel regression method for complex processes. Inspired by attention...

Particulate matter (PM) in the air can cause various health problems and diseases humans. In particular, smaller size of PM2.5 enable them to penetrate deep into lungs, causing severe impacts. Exposure result respiratory, cardiovascular, allergic diseases, prolonged exposure has also been linked an increased risk cancer, including lung cancer. Therefore, forecasting concentration surrounding is crucial for preventing these adverse effects. This paper proposes a method after 1 h using...

In recent years, battery fires have become more common owing to the increased use of lithium-ion batteries. Therefore, monitoring technology is required detect anomalies because cause significant damage systems. We used Mahalanobis distance (MD) and independent component analysis (ICA) early faults in a real-world energy storage system (ESS). The fault types included historical data overvoltage humidity anomaly alarms generated by management program. These are typical preliminary symptoms...

This paper proposes a method for forecasting surface solar irradiance (SSI), the most critical factor in photovoltaic (PV) power generation. The proposed uses 16-channel data obtained by GEO-KOMPSAT-2A (GK2A) satellite of South Korea as main SSI forecasting. To determine feature variables related to from data, differences and ratios between channels were utilized. Additionally, consider fundamental characteristics originating sun, geometry parameters, such declination (SD), elevation angle...

In manufacturing processes using computerized numerical control (CNC) machines, machine tools are operated repeatedly for a long period machining hard and difficult-to-machine materials, such as stainless steel. These operating conditions frequently result in tool breakage. The failure of significantly degrades the product quality efficiency target process. To solve these problems, various studies have been conducted detecting faults tools. However, most related used only univariate signal...

In modern complex industrial processes, mode changes cause unplanned shutdowns, potentially shortening the lifespan of key equipment and incurring significant maintenance costs. To avoid this problem, a method that can detect fault operating in various modes is required. Therefore, we propose novel detection uses k-nearest neighbor normalization-based weight local outlier factor (WLOF). The proposed performs normalization using neighbors to consider possible normal data WLOF used for...

Severe air pollution problems continue to increase because of accelerated industrialization and urbanization. Specifically, fine particulate matter (PM2.5) causes respiratory cardiovascular diseases, according the World Health Organization (WHO), millions premature deaths significant health burdens annually. Therefore, PM2.5 concentration forecasting is essential. This study proposed a method forecast concentrations one hour after using Sequence-to-Sequence Attention (Seq2Seq-attention). The...

Planning an optimal installation site to maximize power-generation efficiency is crucial for the effective operation of photovoltaic power plants. Achieving this requires accurate, reliable information on solar irradiation across different regions. However, ground-based measurements using pyranometers are resource-intensive, requiring substantial time and human effort, their measurement range limited, complicating data collection. To address this, we propose a method accurately estimate...

Accurate and timely fault detection isolation (FDI) improve the availability, safety, reliability of target systems enable cost-effective operations. In this study, a shared nearest neighbor (SNN)-based method is proposed to identify variables circulating fluidized bed boiler. SNN derivative k-nearest (kNN), which utilizes information. The distance information between these neighbors can be applied FDI. particular, effectively detect faults by weighing values based on number they share,...

Machine tools are used in a wide range of applications, and they can manufacture workpieces flexibly. Furthermore, require maintenance; the overall costs include maintenance costs, which constitute significant portion, involved ensuring product quality. Therefore, anomaly detection tool conditions is required, because these essential industrial elements. However, data related to present some challenges: imbalances deficiencies. Data deficiencies affect performance models. A model trained...

Industrial Control System(ICS), which controls facilities at major industrial sites, is increasingly connected to other systems through networks. With this integration and the development of intelligent attacks that can lead a single external intrusion as whole system paralysis, risk impact security on control are increasing. As result, research how protect detect cyber actively underway, deep learning models in form unsupervised have achieved lot, many abnormal detection technologies based...