Predictive Maintenance

The work develops and investigates the hardware and software architecture of an IoT-node for automated monitoring of key parameters of the technological process of bread production. The proposed node, based on the NodeMCU V3 microcontroller (ESP8266), integrates four types of primary transducers: DHT22 (temperature and humidity), MQ-2 (CO₂ gas level), HC-SR04 (liquid level in mixing tanks), and HC-SR501 (personnel presence in production areas).

This paper presents a comprehensive study on the application of modern machine learning methods for predictive maintenance based on the open AI4I Predictive Maintenance dataset. The primary goal of the research is to develop and compare both binary and multiclass classification models that enable not only the prediction of machine failures but also the identification of specific failure types.

This study extends previous research on Remaining Useful Life (RUL) prediction for agricultural vehicles by utilizing an enriched dataset to overcome earlier limitations in forecasting RUL for electric and hydraulic system components. Influential features have been identified through Pearson correlation and Random Forest feature importance analysis. Discrete Wavelet Transform (DWT) has been applied to extract additional approximation and detail coefficients, enhancing the feature set.

The article examines the advantages and disadvantages of an algorithm used to determine the time interval for a monitored object to reach a specific vibration level for use in predictive maintenance in Industry 4.0. The studied algorithm will potentially predict how long before an object fails, helping to reduce downtime and maintain production flow

In the dynamic landscape of modern agriculture, ensuring the reliability and efficiency of machinery is a critical challenge. This article proposes an innovative platform for monitoring and detecting failures in agricultural machinery, harnessing the power of Internet of Things (IoT) technology and cloud computing. The system in AWS cloud receives data from vehicles in real-time and can predict potential failures in engine, transmission, electric and hydraulic systems using machine learning algorithm LSTM.

Timely detection and prevention of agriculture vehicles malfunctions are key approaches to reducing maintenance costs, as well as updating and replacing equipment, and reducing the cost of growing agricultural crops. In this article an approach for Remaining Useful Life (RUL) prediction that utilizes a combination of telemetry, maintenance, and geospatial data (such as weather and terrain information) as input to a Long Short- Term Memory (LSTM) algorithm has been considered.

The article explores the benefits and importance of predictive maintenance in Industry 4.0. It is a revolutionary ap- proach that analyzes data from cyber-physical systems to predict possible equipment failures before they occur and technology applied to detect early signs of a vibration problem on equipment. Thus, downtime is minimized and production continuity is ensured.

The paper presents a brief description of engineering and scientific problems which arise at the steel plant PJSC “ArcelorMittal Kryvyi Rih” when organizing a repair workshop to fix industrial equipment.
The attention is paid to innovative methods of repair process based on intelligent agents and Industry 4.0 principles.