International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

This study presents a correlation-based approach for both detecting sensor malfunctions and identifying redundant sensors in a multi-sensor condition monitoring system. Sensor malfunctions were detected using a threshold-based method that flagged correlation drops, with persistence criteria applied to eliminate false positives. While no persistent malfunctions were observed during the study, the developed algorithm remains suitable for real-time deployment. Correlation analysis also revealed that the 3axis_Y signal exhibited the highest average correlation with others, indicating redundancy. Five machine learning models were trained and evaluated with the Leave-
One-Run-Out strategy to guarantee generalization across acquisition sessions. The findings demonstrated that correlation-driven sensor selection and anomaly detection are effective tools for optimizing predictive maintenance systems, improving model generalization, and simplifying sensor networks without sacrificing reliability.

This study evaluates the performance of newly designed deep-learning model—bidirectional long short-term memory network (Bi-LSTM), with baseline to a conventional multilayer perceptron (MLP)—for classification faults of rolling-element bearings from raw vibration signals. The models are benchmarked against a previously optimised one-dimensional convolutional neural network (1-D CNN), originally obtained via Bayesian hyperparameter search. A carefully selected dataset of 3600 one-second segments was captured under varying speed conditions and dynamically enhanced with Gaussian noise during processing. On the test set, the Bi-LSTM achieves 100 % accuracy, the 1-D CNN 97.9 %, and the MLP 53.3 %. Training dynamics, confusion patterns, and model complexity were thoroughly analysed, highlighting the trade-offs between accuracy, latency and deployment cost in edge-computing scenarios.

Man, as a mechanical system, is extremely complex and his mechanical properties readily undergo change. There is limited reliable information on the magnitude of the forces required to produce mechanical damage to the human body. Our interest in devoted to evaluation of harmful shock and vibration effects during transportation on already sick or injured patients, assessing possible health deterioration degree and developing countermeasures.
This article considers the following problems: (1) the determination of the structure and properties of the human body regarded as a mechanical as well as a biological system, (2) the effects of shock and vibration forces on this system in healthy and injured states during ambulance transportation, (3) the protection required by the system under various exposure conditions and the means by which this protection is to be achieved, and (4) tolerance criteria for shock and for vibration exposure in injured state and assessing possibilities of additional health deterioration.
This article introduces methods used for mechanical shock and vibration studies on man. Subsequent sections deal with the mechanical characteristics of the body, the effects of shock and vibration forces on man, the methods and procedures for protection against these forces, and safety criteria.

Every object in nature has an infinite number of vibration frequency and amplitude as called “Natural Vibration Frequency”. Developing computer capacities allow calculating of natural frequencies and shapes of complex structures more accurate and understandable. In this study, a dual-trolley (2×400 tons) heavy-duty overhead gantry crane that can carry loads up to 800 tons was analysed by mathematical and finite element methods. The mathematical method is based on Euler-Bernoulli transverse vibration approach. On the other hand, finite element method is one of the most common numerical methods that can solve many engineering problems in a range from solid mechanics to acoustic. The generated solid model was analysed by the finite element method with the help of ANSYS Workbench 14.5 which is a commonly used analysis program. The obtained values of natural frequencies at mathematical calculations and finite element analysis were compared and presented.

One of the larger aggregates for production nickel in Feni – INDUSTRIES- Macedonia, is assembly machine mixer 1 and mixer 2. The proper functioning of aggregate depends on the prevention and early detection of damaged parts. Given that the aggregate works non-stop for 24 hours, its failure means termination of operation of furnaces for nickel, and thus the entire production. It means a loss of time, deviation from the production plan, loss of markets and loss of a lot of money. It is a very important to constantly monitor the vital parts rightness. Therefore regularly perform frequency analysis of engine bearings and mixer bearings. Aggregate is composed of: motor, hydro coupling, reducer, mechanics coupling, and mixer.

This paper provides the results of frequency analysis of measured vibration of these parts, compared with limited values and recommendations for quick actions in removing the damaged parts in time periods with the least losses. That means pre timely delivery of bearings, preparation of aggregates for quick repairs with a short downtime. You will also be given a techno – economic analysis to save funds by using this method.