An attempt at applying machine learning in diagnosing marine ship engine turbochargers

Abstract

The article presents a diagnosis of turbochargers in the supercharging systems of marine engines in terms of maintenance decisions. The efficiency of turbocharger rotating machines was defined. The operating parameters of turbocharging systems used to monitor the correct operation and diagnose turbochargers were identified. A parametric diagnostic test was performed. Relationships between parameters for use in machine learning were selected. Their credibility was confirmed by the results of the parametric test of the turbocharger system and the main engine, verified by the coefficient of determination. A particularly good fit of the describing functions was confirmed. As determinants of the technical condition of a turbocharger, the relationship between the rotational speed of the engine shaft, the turbocharger rotor assembly and the charging air pressure was assumed. In the process of machine learning, relationships were created between the rotational speed of the engine shaft and the boost pressure, and the indicator of the need for maintenance. The accuracy of the maintenance decisions was confirmed by trends in changes in the efficiency of compressors.

Application of Machine Learning to Classify the Technical Condition of Marine Engine Injectors Based on Experimental Vibration Displacement Parameters

“…Adamkewicz and Nikonchuk applied ML to the diagnosis of MDEs turbochargers [42]. The value of the coefficient of determination confirmed a good fit for the trend of compressor condition changes.…”

Selected Polynomial Identification Techniques to Evaluate Maritime Transport Trends Around Covid-19

“…The element 𝑝 * defines the degree of the polynomial overstated by one. This means that the deterministic part of the series {𝜀 𝑖 } 1≤𝑖≤𝑛 should be approximated by a polynomial of degree 𝑘 = 𝑝 * − 1; 3. we identify the trend in the series {𝜀 𝑡 𝑖 } 1≤𝑖≤𝑛 using a polynomial of 𝑘 degree; 4. we use stepwise regression to determine the significant predictors in the model (1).…”

“…The test statistic of the Ramsey test [35] has the following form: Selection of a polynomial using the Ramsey test 1. for equation (1) we assume 𝑘 = 1; 2. for model (8) we use the Ramsey test; 3. we estimate 𝑝. 𝑣𝑎𝑙; 4. if 𝑝. 𝑣𝑎𝑙 < 0.05 and 𝑘 ≤ 𝑚 then we assume 𝑘 = 𝑘 + 1 and go back to point 2; otherwise, we go to the next point; 5. we identify the trend in the series {𝜀 𝑡 𝑖 } 1≤𝑖≤𝑛 using a polynomial of 𝑘 degree; 6. we use stepwise regression to determine the significant predictors in the model (1).…”

“…Maritime transport is responsible for the transport of nearly 80% of the volume and 70% of the value of international trade in goods, including goods of key importance to the economy, such as food or fuel. It is responsible for 64% of the world's GDP [9, 1,30]. Therefore, this article examines this branch of transport by checking how the global threat affected sea traffic 53. expressed in terms of the gross weight of goods handled in main ports.…”