Intelligent fault diagnosis can be related to applications of machine learning theories to machine fault diagnosis. Although there is a large number of successful examples, there is a gap in the optimization of the hyper-parameters of the machine learning model, which ultimately has a major impact on the performance of the model. Machine learning experts are required to configure a set of hyper-parameter values manually. This work presents a convolutional neural network based data-driven intelligent fault diagnosis technique for rotary machinery which uses model with optimized hyper-parameters and network structure. The proposed technique input raw three axes accelerometer signal as high definition 1-D data into deep learning layers with optimized hyper-parameters. Input is consisted of wide 12,800 × 1 × 3 vibration signal matrix. Model learning phase includes Bayesian optimization that optimizes hyper-parameters of the convolutional neural network. Finally, by using a Convolutional Neural Network (CNN) model with optimized hyper-parameters, classification in one of the 8 different machine states and 2 rotational speeds can be performed. This study accomplished the effective classification of different rotary machinery states in different rotational speeds using optimized convolutional artificial neural network for classification of raw three axis accelerometer signal input. Overall classification accuracy of 99.94% on evaluation set is obtained with the CNN model based on 19 layers. Additionally, more data are collected on the same machine with altered bearings to test the model for overfitting. Result of classification accuracy of 100% on second evaluation set has been achieved, proving the potential of using the proposed technique.

Fault diagnosis is considered as an essential task in rotary machinery as possibility of an early detection and diagnosis of the faulty condition can save both time and money. This work presents developed and novel technique for deep-learning-based data-driven fault diagnosis for rotary machinery. The proposed technique input raw three axes accelerometer signal as high definition 1D image into deep learning layers which automatically extract signal features, enabling high classification accuracy. Unlike the researches carried out by other researchers, accelerometer data matrix with dimensions 6400 × 1 × 3 is used as input for convolutional neural network training. Since convolutional neural networks can recognize patterns across input matrix, it is expected that wide input matrix containing vibration data should yield good classification performance. Using convolutional neural networks (CNN) trained model, classification in one of the four classes can be performed. Additionally, number of kernels of CNN is optimized using grid search, as preliminary studies show that alternating number of kernels impacts classification results. This study accomplished the effective classification of different rotary machinery states using convolutional artificial neural network for classification of raw three axis accelerometer signal input.

One of the most important elements of the reliability structure of a motor vessel is its power subsystem, with the most crucial component being the engine. An engine failure excludes the ship from operation or significantly limits its operation. Therefore, accurate fault diagnosis should be a crucial issue for modern maintenance strategies. In mechanical engineering, the vibration and acoustic signals recorded during the operation of the device are the most meaningful data used to identify the reliability state. In this paper, a novel system-oriented method of reliability state identification is proposed. The method consists of the analysis of the vibration and noise signals collected on each of the engine cylinders using supervised machine learning. The main novelty of this method is data augmentation application and SVM classifier implementation. Due to these aspects, the method becomes robust in the case of poor-quality data or a limited and incomplete learning dataset. The quality of the proposed identification method was evaluated by addressing a new industrial issue (Sulzer 6AL20/24 marine engine reliability state identification). During the tests, the efficiency of the method was analyzed in the case of a complete learning data set (all types of inability states were presented in the learning data set) and an incomplete learning data set (in the testing data set, there were new types of inability states). As a result, in both cases, a very high (100%) identification accuracy of the reliability state and the type of inability state was obtained. This is a significant increase in accuracy (4.6% for the complete and 22% for the incomplete learning data set) in comparison to the efficiency of the same method without the use of machine learning and data science.

The study presents the evaluation and comparative analysis of engine shaft line performance in maritime transport ships of the same type. During its operation, a technical system performs functions for which it was designed. It goes through different states. Dynamic state changes of a rotational system can be identified by means of its vibration measurement. For this purpose, a research was carried out which involved recording vibrations of the analysed rotational systems. The recordings were used for calculating selected characteristics in the time-domain, where one of the most unique is the value of the normalized mutual correlation function. On the basis of the concentration values, the characteristics which unambiguously determine the ability state were selected for further studies. Then an identification method for rotational system non-coaxiality was proposed. The method involves using fuzzy clustering. According to this method the values of input signal characteristics were used to formulate fuzzy clusters of system ability and inability states. The method can be used for identifying the current state of the system. The study presents the results of the application of this method in engine turbine shaft lines of minesweepers, with the rotational system selected as an example. It needs to be noted that the efficiency of identifying the operating state of the system with this method is higher than with other methods described in the literature by authors who deal with this issue. The research results have a significant impact on the evaluation of mechanical properties of the studied objects and directly affect operational states of mechanical systems, including those installed in minesweepers, thus determining their reliability.

The most common indicators used for assessing combustion engines powered by renewable fuels with simultaneous fuel injection are: power, torque, fuel consumption, noise emission, amount of particulates present in the exhaust fumes and composition of exhaust fumes (oxygen, carbon dioxide, hydrocarbons, nitric oxides and air excess coefficient). The aim of this study is to analyze the impact of the addition of fatty acid methyl esters to diesel oil on the value of transport means performance parameters, particularly the level of noise generated by the transport means drive units. Generating noise by internal combustion piston engines is the effect of their operation. Our study compared emissions of sound generated by diesel oil powered with diesel oil and the mixture of 30% of fatty acid methyl esters (biocomponents) and 70% of diesel oil. The object of the study is the piston combustion engine with self-ignition of 80 kW rated power. The experiment was conducted for four scopes of the fuel controller’s settings: standard ones, increased for 2%, 4%, and 6% dosage of fuel and supercharging for 50 mb. We found that the increased dosages of fuel at powering with diesel oil without the additive of biocomponent influences the increase of the noise level within the whole tested scope.

Rubber and rubber-metal vibration isolators are widely used vibration isolation systems in marine applications. For naval application, shock absorber mounting systems must fulfil two functions. The first one supports the suspended mass in the absence of waving or detonation while providing isolation from vibrations and shock impact. In the second case, during the machine operation, it reduces the force of movement to an acceptable value. Moreover, it returns the insulated mass to the position output without plastic deformation or residual buckling after removing shock stresses or harmonic vibrations. The environment in which marine vibration isolators are to be used strongly influences the selection of a shock absorber. The main environmental problem is the temperature range in marine power plants, which ranges from 20 °C to 55 °C. Temperature fluctuations may cause changes in the physical properties of typical vibration/shock insulators. Both rubbers and elastomers used for shock absorbers tend to stiffen, gain low-temperature damping, and soften and lose damping at elevated temperatures. Factors such as moisture, ozone and changes in atmospheric pressure are usually ignored in shipbuilding. The main environmental factors influencing the ageing of insulators are liquid saturated hydrocarbons, i.e., oils, fuels, coolants, etc., which may come into contact with the surface of the insulators. This work presents the results of the research carried out to determine the effect of overload and the impact of petroleum products on the materials of metal-rubber shock absorbers made of three different rubbers and one polyurethane mixture. For each of the materials, shock absorbers with three different degrees of hardness were tested.