Search

The article presents the possibility of using machine learning (ML) in artificial intelligence to classify the technical state of marine engine injectors. The technical condition of the internal combustion engine and injection apparatus significantly determines the composition of the outlet gases. For this purpose, an analytical package using modern technology assigns experimental test scores to appropriate classes. The graded changes in the value of diagnostic parameters were measured on the injection subsystem bench outside the engine. The influence of the operating conditions of the fuel injection subsystem and injector condition features on the injector needle vibration displacement waveforms was subjected to a neural network (NN) ML process and then tested. Diagnostic parameters analyzed in the amplitude, frequency, and time–frequency domains were subjected after a learning process to recognize simulated various regulatory and technical states of suitability and unfitness with single and complex damage of new and worn injector nozzles. Classification results were satisfactory in testing single damage and multiple changes in technical state characteristics for unfitness states with random wear injectors. Testing quality reached above 90% using selected NNs of Statistica 13.3 and MATLAB R2022a environments. [ABSTRACT FROM AUTHOR]

The article presents the possibility of using machine learning (ML) in artificial intelligence to classify the technical state of marine engine injectors. The technical condition of the internal combustion engine and injection apparatus significantly determines the composition of the outlet gases. For this purpose, an analytical package using modern technology assigns experimental test scores to appropriate classes. The graded changes in the value of diagnostic parameters were measured on the injection subsystem bench outside the engine. The influence of the operating conditions of the fuel injection subsystem and injector condition features on the injector needle vibration displacement waveforms was subjected to a neural network (NN) ML process and then tested. Diagnostic parameters analyzed in the amplitude, frequency, and time–frequency domains were subjected after a learning process to recognize simulated various regulatory and technical states of suitability and unfitness with single and complex damage of new and worn injector nozzles. Classification results were satisfactory in testing single damage and multiple changes in technical state characteristics for unfitness states with random wear injectors. Testing quality reached above 90% using selected NNs of Statistica 13.3 and MATLAB R2022a environments.

The task of classifying the entanglement properties of a multipartite quantum state poses a remarkable challenge due to the exponentially increasing number of ways in which quantum systems can share quantum correlations. Tackling such challenge requires a combination of sophisticated theoretical and computational techniques. In this paper we combine machine-learning tools and the theory of quantum entanglement to perform entanglement classification for multipartite qubit systems in pure states. We use a parameterisation of quantum systems using artificial neural networks in a restricted Boltzmann machine architecture, known as Neural Network Quantum States, whose entanglement properties can be deduced via a constrained, reinforcement learning procedure. In this way, Separable Neural Network States can be used to build entanglement witnesses for any target state.