Search Results

Misfire represents a crucial problem for vehicles, adding to the energy depletion in the midst of air pollution such as CO and NOx caused by exhaust gases. Because of a special cylinder, misfire produces a particular vibration pattern. These patterns can isolate and interpret valuable properties to detect misfires. In this paper, a machine learning approach is used as a predictive model for the identification of misfires. In the current research, vibratory signals were taken as a kind of misfire that is unique to each cylinder (acquired with the help of a piezoelectric accelerometer). Statistical characteristics are then extracted and feature selection is applied using the J48 decision tree algorithm from the features obtained. In the classification of misfires in the cylinders, the K* classification was used. The experiment was conducted in Maruti Suzuki Baleno. Every single cylinder was tested on a separate basis.

Even though hydraulic brakes are valuable safety elements for riders, they are necessary for braking in a good condition. Vibration signatures may be used to assess the condition of the brake components. In this research, the monitor and make status tracking and the dynamic data acquisition method with a piezo-electric transducer is suggested as a promising approach to these challenges by machine-learning. The Ford EcoSport rig was used to get the vibration signal for good and bad braking conditions. The vibration signals had analytical mathematical predictive characteristics, and the decision tree model, J48 was used in the selection of the signals. In order to define a certain concern, a structural decision does not state the number of features required. Therefore, to find the right number of features a rigorous analysis is required.

Car hydraulic brakes are important safety components for passengers and are thus the good condition of brakes are essential for braking. By using the vibrational signatures, the state of the brake components can be determined. In this proposed study, electronic condition monitoring is suggested as a possible solution to such issues by using a machine learning method with a piezo-electric transducer and a dynamic data acquisition system. Ford EcoSport setup was used to acquire the vibration signals for both good and bad braking conditions. The mathematical Descriptive statistical features from the vibration signals were obtained and the feature selection has been done with the C4.5 decision tree classifier. The appropriate number of features needed to classify a particular problem is not determined by a specific method. A thorough study is, therefore, necessary to find the right number of features.