# Optimization of the Spatial Position of the Vibration Acceleration Sensor and the Method of Determining Limit Values in the Diagnostics of Combustion Engine Injection System

## TL;DR

This paper introduces a new method for diagnosing issues in marine engine fuel injection systems using vibration sensors and machine learning.

## Contribution

The paper presents a novel diagnostic procedure using optimized sensor placement and new limit values for classification.

## Key findings

- Vibration signals are strongest when the sensor is placed on the injection pipe.
- New tolerance ranges for diagnostic limits are calculated using mean and standard error.
- Machine learning models achieve 70% testing accuracy in classifying system states.

## Abstract

A new procedure for diagnosing damage to the fuel injection system of marine engines, along with vibration acceleration signal symptoms, is explored with a related built, developed, and tested measuring system. This work fills an important gap given the current lack of a scientific solution to this problem. A vibration acceleration signal sensor, mounted on a holder elaborated on by the authors, is positioned on the injection pipe between the injection pump and the injector. The output signals from the sensor are sent to an acquisition and analysis system, which is used for processing the signals in the time, amplitude, frequency, and time–frequency domains. Experimental choices, using multiple parameters for a given signal analysis field, are based on the location of the optimal sensor, the direction of the sensor mounting, and the selection of a cumulative diagnostic symptom. The vibration acceleration signals recorded along the injection pipe are found to have the strongest magnitude. This article compares diagnostic values from these signals with previously determined upper and lower limits. As a result, the tested fuel injection system is classified as either able or disabled, using unparalleled tolerance ranges given for both the upper and lower limits. The values of the limits are determined based on the average value for an ability state plus or minus three times the standard error of this mean, which has not been reported in the literature previously. Multiple regression models are developed that relate identified symptoms to the state features of the fuel injection system. In addition, artificial neural networks and machine learning are used to detect developing damage. The probability of correctly classifying the states of the diagnostic parameters is 0.467, alongside a diagnostic accuracy of ≤±4%, with the network correctly classifying the state when the testing accuracy is at least 70.0%.